def check_time_extents(self, ds):
"""
Check that the values of time_coverage_start/time_coverage_end approximately match the data.
"""
if not (hasattr(ds, 'time_coverage_start') and hasattr(ds, 'time_coverage_end')):
return
# Parse the ISO 8601 formatted dates
try:
t_min = dateparse(ds.time_coverage_start)
t_max = dateparse(ds.time_coverage_end)
except:
return Result(BaseCheck.MEDIUM,
False,
'time_coverage_extents_match',
['time_coverage attributes are not formatted properly. Use the ISO 8601:2004 date format, preferably the extended format.'])
timevar = cfutil.get_time_variable(ds)
if not timevar:
return Result(BaseCheck.MEDIUM,
False,
'time_coverage_extents_match',
['Could not find time variable to test extent of time_coverage_start/time_coverage_end, see CF-1.6 spec chapter 4.4'])
# Time should be monotonically increasing, so we make that assumption here so we don't have to download THE ENTIRE ARRAY
try:
# num2date returns as naive date, but with time adjusted to UTC
# we need to attach timezone information here, or the date
# subtraction from t_min/t_max will assume that a naive timestamp is
# in the same time zone and cause erroneous results.
# Pendulum uses UTC by default, but we are being explicit here
time0 = pendulum.instance(num2date(ds.variables[timevar][0],
ds.variables[timevar].units), 'UTC')
time1 = pendulum.instance(num2date(ds.variables[timevar][-1],
ds.variables[timevar].units), 'UTC')
except:
return Result(BaseCheck.MEDIUM,
False,
'time_coverage_extents_match',
['Failed to retrieve and convert times for variables %s.' % timevar])
start_dt = abs(time0 - t_min)
end_dt = abs(time1 - t_max)
score = 2
msgs = []
if start_dt > timedelta(hours=1):
msgs.append("Date time mismatch between time_coverage_start and actual "
"time values %s (time_coverage_start) != %s (time[0])" % (t_min.isoformat(), time0.isoformat()))
score -= 1
if end_dt > timedelta(hours=1):
msgs.append("Date time mismatch between time_coverage_end and actual "
"time values %s (time_coverage_end) != %s (time[N])" % (t_max.isoformat(), time1.isoformat()))
score -= 1
return Result(BaseCheck.MEDIUM,
(score, 2),
'time_coverage_extents_match',
msgs)
def get_applicable_variables(self, ds):
'''
Returns a list of variable names that are applicable to ACDD Metadata
Checks for variables. This includes geophysical and coordinate
variables only.
:param netCDF4.Dataset ds: An open netCDF dataset
'''
if self._applicable_variables is None:
self.applicable_variables = cfutil.get_geophysical_variables(ds)
varname = cfutil.get_time_variable(ds)
# avoid duplicates by checking if already present
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
varname = cfutil.get_lon_variable(ds)
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
varname = cfutil.get_lat_variable(ds)
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
varname = cfutil.get_z_variable(ds)
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
return self.applicable_variables
def get_applicable_variables(self, ds):
"""
Returns a list of variable names that are applicable to ACDD Metadata
Checks for variables. This includes geophysical and coordinate
variables only.
:param netCDF4.Dataset ds: An open netCDF dataset
"""
if self._applicable_variables is None:
self.applicable_variables = cfutil.get_geophysical_variables(ds)
varname = cfutil.get_time_variable(ds)
# avoid duplicates by checking if already present
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
varname = cfutil.get_lon_variable(ds)
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
varname = cfutil.get_lat_variable(ds)
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
varname = cfutil.get_z_variable(ds)
if varname and (varname not in self.applicable_variables):
self.applicable_variables.append(varname)
return self.applicable_variables
def check_time_extents(self, ds):
"""
Check that the values of time_coverage_start/time_coverage_end approximately match the data.
"""
if not (hasattr(ds, 'time_coverage_start') and hasattr(ds, 'time_coverage_end')):
return
# Parse the ISO 8601 formatted dates
try:
t_min = dateparse(ds.time_coverage_start)
t_max = dateparse(ds.time_coverage_end)
except:
return Result(BaseCheck.MEDIUM,
False,
'time_coverage_extents_match',
['time_coverage attributes are not formatted properly. Use the ISO 8601:2004 date format, preferably the extended format.'])
timevar = cfutil.get_time_variable(ds)
if not timevar:
return Result(BaseCheck.MEDIUM,
False,
'time_coverage_extents_match',
['Could not find time variable to test extent of time_coverage_start/time_coverage_end, see CF-1.6 spec chapter 4.4'])
# Time should be monotonically increasing, so we make that assumption here so we don't have to download THE ENTIRE ARRAY
try:
# num2date returns as naive date, but with time adjusted to UTC
# we need to attach timezone information here, or the date
# subtraction from t_min/t_max will assume that a naive timestamp is
# in the same time zone and cause erroneous results.
# Pendulum uses UTC by default, but we are being explicit here
time0 = pendulum.instance(num2date(ds.variables[timevar][0],
ds.variables[timevar].units), 'UTC')
time1 = pendulum.instance(num2date(ds.variables[timevar][-1],
ds.variables[timevar].units), 'UTC')
except:
return Result(BaseCheck.MEDIUM,
False,
'time_coverage_extents_match',
['Failed to retrieve and convert times for variables %s.' % timevar])
start_dt = abs(time0 - t_min)
end_dt = abs(time1 - t_max)
score = 2
msgs = []
if start_dt > timedelta(hours=1):
msgs.append("Date time mismatch between time_coverage_start and actual "
"time values %s (time_coverage_start) != %s (time[0])" % (t_min.isoformat(), time0.isoformat()))
score -= 1
if end_dt > timedelta(hours=1):
msgs.append("Date time mismatch between time_coverage_end and actual "
"time values %s (time_coverage_end) != %s (time[N])" % (t_max.isoformat(), time1.isoformat()))
score -= 1
return Result(BaseCheck.MEDIUM,
(score, 2),
'time_coverage_extents_match',
msgs)
def check_time_extents(self, ds):
"""
Check that the values of time_coverage_start/time_coverage_end approximately match the data.
"""
if not (hasattr(ds, 'time_coverage_start')
and hasattr(ds, 'time_coverage_end')):
return
# allows non-ISO 8601 formatted dates
try:
t_min = dateparse(ds.time_coverage_start)
t_max = dateparse(ds.time_coverage_end)
except:
return Result(
BaseCheck.MEDIUM, False, 'time_coverage_extents_match', [
'time_coverage variables are not formatted properly. Please ensure they are valid ISO-8601 time strings'
])
timevar = cfutil.get_time_variable(ds)
if not timevar:
return Result(
BaseCheck.MEDIUM, False, 'time_coverage_extents_match', [
'Could not find time variable to test extent of time_coverage_start/time_coverage_end, see CF-1.6 spec chapter 4.4'
])
# Time should be monotonically increasing, so we make that assumption here so we don't have to download THE ENTIRE ARRAY
try:
time0 = num2date(ds.variables[timevar][0],
ds.variables[timevar].units)
time1 = num2date(ds.variables[timevar][-1],
ds.variables[timevar].units)
except:
return Result(
BaseCheck.MEDIUM, False, 'time_coverage_extents_match', [
'Failed to retrieve and convert times for variables %s.' %
timevar
])
start_dt = abs(time0 - t_min)
end_dt = abs(time1 - t_max)
score = 2
msgs = []
if start_dt > timedelta(hours=1):
msgs.append(
"Date time mismatch between time_coverage_start and actual "
"time values %s (time_coverage_start) != %s (time[0])" %
(t_min.isoformat(), time0.isoformat()))
score -= 1
if end_dt > timedelta(hours=1):
msgs.append(
"Date time mismatch between time_coverage_end and actual "
"time values %s (time_coverage_end) != %s (time[N])" %
(t_max.isoformat(), time1.isoformat()))
score -= 1
return Result(BaseCheck.MEDIUM, (score, 2),
'time_coverage_extents_match', msgs)
def get_applicable_variables(self, ds):
'''
Returns a list of variable names that are applicable to ACDD Metadata
Checks for variables. This includes geophysical and coordinate
variables only.
:param netCDF4.Dataset ds: An open netCDF dataset
'''
if self._applicable_variables is None:
self.applicable_variables = cfutil.get_geophysical_variables(ds)
varname = cfutil.get_time_variable(ds)
if varname:
self.applicable_variables.append(varname)
varname = cfutil.get_lon_variable(ds)
if varname:
self.applicable_variables.append(varname)
varname = cfutil.get_lat_variable(ds)
if varname:
self.applicable_variables.append(varname)
varname = cfutil.get_z_variable(ds)
if varname:
self.applicable_variables.append(varname)
return self.applicable_variables