def test_value_check_numeric_ranges():
"""Test value checks with numerical range functions."""
field_names = ('foo', 'bar', 'baz', 'quux')
validator = CSVValidator(field_names)
validator.add_value_check('foo', number_range_inclusive(2, 6, int))
validator.add_value_check('bar', number_range_exclusive(2, 6, int))
validator.add_value_check('baz', number_range_inclusive(2.0, 6.3, float))
validator.add_value_check('quux', number_range_exclusive(2.0, 6.3, float))
data = (
('foo', 'bar', 'baz', 'quux'),
('2', '3', '2.0', '2.1'), # valid
('1', '3', '2.0', '2.1'), # foo invalid
('2', '2', '2.0', '2.1'), # bar invalid
('2', '3', '1.9', '2.1'), # baz invalid
('2', '3', '2.0', '2.0') # quux invalid
)
problems = validator.validate(data)
assert len(problems) == 4, len(problems)
for p in problems:
assert p['code'] == VALUE_CHECK_FAILED
assert problems[0]['row'] == 3 and problems[0]['field'] == 'foo'
assert problems[1]['row'] == 4 and problems[1]['field'] == 'bar'
assert problems[2]['row'] == 5 and problems[2]['field'] == 'baz'
assert problems[3]['row'] == 6 and problems[3]['field'] == 'quux'
def test_value_check_numeric_ranges():
"""Test value checks with numerical range functions."""
field_names = ('foo', 'bar', 'baz', 'quux')
validator = CSVValidator(field_names)
validator.add_value_check('foo', number_range_inclusive(2, 6, int))
validator.add_value_check('bar', number_range_exclusive(2, 6, int))
validator.add_value_check('baz', number_range_inclusive(2.0, 6.3, float))
validator.add_value_check('quux', number_range_exclusive(2.0, 6.3, float))
data = (
('foo', 'bar', 'baz', 'quux'),
('2', '3', '2.0', '2.1'), # valid
('1', '3', '2.0', '2.1'), # foo invalid
('2', '2', '2.0', '2.1'), # bar invalid
('2', '3', '1.9', '2.1'), # baz invalid
('2', '3', '2.0', '2.0') # quux invalid
)
problems = validator.validate(data)
assert len(problems) == 4, len(problems)
for p in problems:
assert p['code'] == VALUE_CHECK_FAILED
assert problems[0]['row'] == 3 and problems[0]['field'] == 'foo'
assert problems[1]['row'] == 4 and problems[1]['field'] == 'bar'
assert problems[2]['row'] == 5 and problems[2]['field'] == 'baz'
assert problems[3]['row'] == 6 and problems[3]['field'] == 'quux'
def create_validator():
"""Create an example CSV validator for patient demographic data."""
field_names = ('study_id', 'patient_id', 'gender', 'age_years',
'age_months', 'date_inclusion')
validator = CSVValidator(field_names)
# basic header and record length checks
validator.add_header_check('EX1', 'bad header')
validator.add_record_length_check('EX2', 'unexpected record length')
# some simple value checks
validator.add_value_check('study_id', int, 'EX3',
'study id must be an integer')
validator.add_value_check('patient_id', int, 'EX4',
'patient id must be an integer')
validator.add_value_check('gender', enumeration('M', 'F'), 'EX5',
'invalid gender')
validator.add_value_check('age_years', number_range_inclusive(0, 120, int),
'EX6', 'invalid age in years')
validator.add_value_check('date_inclusion', datetime_string('%Y-%m-%d'),
'EX7', 'invalid date')
# a more complicated record check
def check_age_variables(r):
age_years = int(r['age_years'])
age_months = int(r['age_months'])
valid = (age_months >= age_years * 12 and age_months % age_years < 12)
if not valid:
raise RecordError('EX8', 'invalid age variables')
validator.add_record_check(check_age_variables)
return validator
def create_validator():
"""Create an example CSV validator for patient demographic data."""
field_names = (
'study_id',
'patient_id',
'gender',
'age_years',
'age_months',
'date_inclusion'
)
validator = CSVValidator(field_names)
# basic header and record length checks
validator.add_header_check('EX1', 'bad header')
validator.add_record_length_check('EX2', 'unexpected record length')
# some simple value checks
validator.add_value_check('study_id', int,
'EX3', 'study id must be an integer')
validator.add_value_check('patient_id', int,
'EX4', 'patient id must be an integer')
validator.add_value_check('gender', enumeration('M', 'F'),
'EX5', 'invalid gender')
validator.add_value_check('age_years', number_range_inclusive(0, 120, int),
'EX6', 'invalid age in years')
validator.add_value_check('date_inclusion', datetime_string('%Y-%m-%d'),
'EX7', 'invalid date')
# a more complicated record check
def check_age_variables(r):
age_years = int(r['age_years'])
age_months = int(r['age_months'])
valid = (age_months >= age_years * 12 and
age_months % age_years < 12)
if not valid:
raise RecordError('EX8', 'invalid age variables')
validator.add_record_check(check_age_variables)
return validator
