def test_unique_validator_fails(fields, row, unique_with, exception, bad):
validator = UniqueValidator(unique_with=unique_with)
with pytest.raises(exception):
for field in fields:
validator.validate(field, row)
assert validator.bad == bad
class YourFirstNonCommaDelimitedValidator(Vlad):
source = LocalFile("bats.csv")
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
}
delimiter = "|"
def test_initialize_vlad():
source = LocalFile('vladiate/examples/vampires.csv')
validators = {
'Column A': [UniqueValidator()],
'Column B': [SetValidator(['Vampire', 'Not A Vampire'])]
}
assert Vlad(source=source, validators=validators).validate()
def test_initialize_vlad():
source = LocalFile("vladiate/examples/vampires.csv")
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
}
assert Vlad(source=source, validators=validators).validate()
class Validator(Vlad):
source = LocalFile("repos.csv")
validators = {
"contact": [
RegexValidator(r"\w[\w\-' ]+ <[\w\-.]+@[\w\-.]+>",
full=True,
empty_ok=True)
],
"doi": [RegexValidator(r"[\w\-./]+", full=True, empty_ok=True)],
"funders": [RegexValidator(r"(\d+;?)+", full=True, empty_ok=True)],
"homepage_url":
[RegexValidator(r"https?://.+", full=True, empty_ok=True)],
"licence": [
SetValidator(
[
"Apache-2.0",
"Artistic-2.0",
"BSD-2-Clause",
"BSD-3-Clause",
"CECILL-2.1",
"GPL-2.0",
"GPL-3.0",
"MIT",
"MPL-2.0",
"NCSA",
],
empty_ok=True,
)
],
"organisations":
[SetValidator(["grid.457348.9", "grid.4991.5"], empty_ok=True)],
"rsotm": [RegexValidator(r"\d{4}-\d{2}", full=True, empty_ok=True)],
"url": [UniqueValidator()],
}
def test_initialize_vlad_with_alternative_delimiter():
source = LocalFile('vladiate/examples/bats.csv')
validators = {
'Column A': [UniqueValidator()],
'Column B': [SetValidator(['Vampire', 'Not A Vampire'])]
}
delimiter = '|'
vlad = Vlad(source=source, validators=validators, delimiter=delimiter)
assert vlad.validate()
def test_unused_validator_fails_validation():
source = LocalFile('vladiate/examples/vampires.csv')
validators = {
'Column A': [UniqueValidator()],
'Column B': [SetValidator(['Vampire', 'Not A Vampire'])],
'Column C': [FloatValidator()]
}
assert not Vlad(source=source, validators=validators).validate()
def test_unused_validator_fails_validation():
source = LocalFile("vladiate/examples/vampires.csv")
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
"Column C": [FloatValidator()],
}
assert not Vlad(source=source, validators=validators).validate()
def test_initialize_vlad_with_alternative_delimiter():
source = LocalFile("vladiate/examples/bats.csv")
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
}
delimiter = "|"
vlad = Vlad(source=source, validators=validators, delimiter=delimiter)
assert vlad.validate()
class YourFirstValidator(Vlad):
source = LocalFile('vampires.csv')
validators = {
'Column A': [
UniqueValidator()
],
'Column B': [
SetValidator(['Vampire', 'Not A Vampire'])
]
}
class YourFirstNonCommaDelimitedValidator(Vlad):
source = LocalFile('bats.csv')
validators = {
'Column A': [
UniqueValidator()
],
'Column B': [
SetValidator(['Vampire', 'Not A Vampire'])
]
}
delimiter = '|'
# We could do the validation directioly in the first read block below
# But for now let's add an additional read through the data
# Annoyingly, you have to instantiate that "validators" block for each record
# Otherwise they seem to accumulate extra values.
# Beyond the 2 new validators defined above, we're using vladiate defined options
allgood = True
badfiles = []
for sfn in os.listdir(args.indir + args.sub):
if sfn not in skip and sfn.endswith(".tsv"):
validators = {
'docId': [
UniqueValidator(unique_with=['annotSet', 'annotId']),
#UniqueValidator(unique_with=['annotSet', 'startOffset'])
],
'annotId': [RegexValidator(pattern=r'T?\d*-?\d+', full=True)],
'annotType': [
SetValidator([
'Quantity', 'Qualifier', 'MeasuredProperty',
'MeasuredEntity'
])
],
'annotSet': [IntValidator()],
'startOffset': [IntValidator()],
'endOffset': [IntValidator()],
'other': [JsonValidator(empty_ok=True)],
'text': [LengthValidator()]
}
def test_unique_validator_works(fields, row, unique_with):
validator = UniqueValidator(unique_with=unique_with)
for field in fields:
validator.validate(field, row)
class TestVlad(Vlad):
validators = {
'Column A': [UniqueValidator()],
'Column B': [SetValidator(['Vampire', 'Not A Vampire'])]
}
class TestVlad(Vlad):
validators = {
'Column A': [UniqueValidator()],
}
class TestVlad(Vlad):
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
}
class TestVlad(Vlad):
validators = {"Column A": [UniqueValidator()]}
class YourFirstValidator(Vlad):
source = LocalFile("vampires.csv")
validators = {
"Column A": [UniqueValidator()],
"Column B": [SetValidator(["Vampire", "Not A Vampire"])],
}
class WeatherValidator(Vlad):
source = TOA5Input('SPER_CR6_Daily.dat')
validators = {
'TIMESTAMP': [
RegexValidator(
pattern=
"((19|20)\\d\\d)-(0?[1-9]|1[012])-(0?[1-9]|[12][0-9]|3[01]) ([2][0-3]|[0-1][0-9]|[1-9]):[0-5][0-9]:([0-5][0-9]|[6][0])$",
empty_ok=False)
],
'RECORD': [UniqueValidator(empty_ok=False)],
'BattV_Min':
[RangeValidator(low=float(columns[1][2]), high=float(columns[2][2]))],
'WS_ms_Avg':
[RangeValidator(low=float(columns[1][3]), high=float(columns[2][3]))],
'WS_ms_Max':
[RangeValidator(low=float(columns[1][4]), high=float(columns[2][4]))],
'WS_ms_TMx': [
RegexValidator(
pattern=
"((19|20)\\d\\d)-(0?[1-9]|1[012])-(0?[1-9]|[12][0-9]|3[01]) ([2][0-3]|[0-1][0-9]|[1-9]):[0-5][0-9]:([0-5][0-9]|[6][0])$",
empty_ok=False)
],
'WS_ms_S_WVT':
[RangeValidator(low=float(columns[1][6]), high=float(columns[2][6]))],
'WindDir_D1_WVT':
[RangeValidator(low=float(columns[1][7]), high=float(columns[2][8]))],
'WindDir_SD1_WVT':
[RangeValidator(low=float(columns[1][8]), high=float(columns[2][9]))],
'SlrMJ_Tot': [
RangeValidator(low=float(columns[1][10]),
high=float(columns[2][10]))
],
'Rain_mm_Tot': [
RangeValidator(low=float(columns[1][11]),
high=float(columns[2][11]))
],
'AirTC_Avg': [
RangeValidator(low=float(columns[1][12]),
high=float(columns[2][12]))
],
'AirTC_Max': [
RangeValidator(low=float(columns[1][13]),
high=float(columns[2][13]))
],
'AirTC_TMx': [
RegexValidator(
pattern=
"((19|20)\\d\\d)-(0?[1-9]|1[012])-(0?[1-9]|[12][0-9]|3[01]) ([2][0-3]|[0-1][0-9]|[1-9]):[0-5][0-9]:([0-5][0-9]|[6][0])$",
empty_ok=False)
],
'AirTC_Min': [
RangeValidator(low=float(columns[1][14]),
high=float(columns[2][14]))
],
'AirTC_TMn': [
RegexValidator(
pattern=
"((19|20)\\d\\d)-(0?[1-9]|1[012])-(0?[1-9]|[12][0-9]|3[01]) ([2][0-3]|[0-1][0-9]|[1-9]):[0-5][0-9]:([0-5][0-9]|[6][0])$",
empty_ok=False)
],
'RH_Max': [
RangeValidator(low=float(columns[1][16]),
high=float(columns[2][16]))
],
'RH_TMx': [
RegexValidator(
pattern=
"((19|20)\\d\\d)-(0?[1-9]|1[012])-(0?[1-9]|[12][0-9]|3[01]) ([2][0-3]|[0-1][0-9]|[1-9]):[0-5][0-9]:([0-5][0-9]|[6][0])$",
empty_ok=False)
],
'RH_Min': [
RangeValidator(low=float(columns[1][18]),
high=float(columns[2][18]))
],
'RH_TMn': [
RegexValidator(
pattern=
"((19|20)\\d\\d)-(0?[1-9]|1[012])-(0?[1-9]|[12][0-9]|3[01]) ([2][0-3]|[0-1][0-9]|[1-9]):[0-5][0-9]:([0-5][0-9]|[6][0])$",
empty_ok=False)
]
}
def test_unique_validator_supports_empty_ok(fields, row, unique_with):
validator = UniqueValidator(unique_with=unique_with, empty_ok=True)
for field in fields:
validator.validate(field, row)