def checkURL(self, url):
msg = False
try:
request = urllib.request.urlopen(url)
if request.code == 200:
if request.code == 200 and not url.startswith('https://'):
try:
tmp = url.split('//')
request = requests.get("https://" + tmp[-1])
msg = errors.http()
except:
msg = errors.okay()
elif request.code < 400 and request.code >= 300:
msg = errors.check_link()
elif request.code >= 400:
msg = errors.broken_url()
else:
msg = errors.check_link()
except urllib.request.HTTPError as e:
msg = errors.broken_url()
except urllib.request.URLError as e:
msg = errors.check_link()
if not msg and not url.startswith('ftp'):
msg = errors.okay()
elif url.startswith('ftp'):
msg = errors.ftp()
else:
pass
return msg
def checkEquatorCrossingTime(self, val, length):
#print("Input of checkEquatorCrossingTime() is ...")
if length == 1:
return self.__checkTimeStr(
val, errors.not_provided(), errors.okay(),
errors_date_format_error(val),
errors_date_format_day_error(val),
errors_date_format_month_error(val),
errors_date_format_inserttime_future_error(val))
'''
try:
if val == None:
return errors.not_provided()
if not val.endswith("Z"):
return "DateTime error"
val = val.replace("Z", "")
t_record = datetime.strptime(val, '%Y-%m-%dT%H:%M:%S')
if t_record.microsecond / 1000 > 999:
return "DateTime error"
t_now = datetime.now()
if t_record.year > t_now.year:
return "DateTime error"
return "OK - quality check"
except ValueError:
return "DateTime error"
'''
else:
for i in range(0, length):
return self.__checkTimeStr(
val['EquatorCrossingDateTime'], errors.not_provided(),
errors.okay(), errors_date_format_error(val),
errors_date_format_day_error(val),
errors_date_format_month_error(val),
errors_date_format_inserttime_future_error(val))
'''
def checkCollectionVersionID(self, sname):
#print("Input of checkCollectionVersionID() is " + sname)
if sname == None:
return "np - Ensure the DataSetId field is provided."
else:
return errors.okay()
def checkTemporalSingleTime(self, val):
#print("Input of checkTemporalSingleTime() is " + val)
return self.__checkTimeStr(
val, errors.not_provided(), errors.okay(),
errors_date_format_error(val), errors_date_format_day_error(val),
errors_date_format_month_error(val),
errors_date_format_inserttime_future_error(val))
'''
def checkProductionDateTime(self, prodTime, insertTime):
#print("Input of checkProductionDateTime() is " + prodTime + ', ' + insertTime)
return self.__checkTimeStr(
val, errors.not_provided(), errors.okay(),
errors_date_format_error(val), errors_date_format_day_error(val),
errors_date_format_month_error(val),
errors_date_format_inserttime_future_error(val))
'''
def checkDataSetId(set, val):
#print("Input of checkDataSetId() is " + val)
if val == None:
return "np - Ensure that the ShortName and VersionId fields are provided."
elif val.isupper() or val.islower():
return "Recommend that the Dataset Id use mixed case to optimize human readability."
else:
return errors.okay()
def checkDayNightFlag(set, val):
#print("Input of checkDayNightFlag() is " + val)
DNFlags = ('DAY', 'NIGHT', 'BOTH', 'UNSPECIFIED')
if val == None:
return errors.not_provided()
elif val.upper() not in DNFlags:
return "Invalid value for DayNightFlag. Valid values include: DAY; NIGHT; BOTH; UNSPECIFIED"
else:
return errors.okay()
def checkOnlineResourceURL(self, val, length):
#print("Input of checkOnlineResourceURL() is ...")
#print("Input of checkOnlineAccessURL() is ...")
check = []
broken = []
okay = []
ftp = []
http = []
if length == 1:
if val == None:
return errors.not_provided()
error = self.checkURL(val) + '\n' + val[i]['URL']
return error
else:
error = ''
for i in range(0, length):
if val[i]['URL'] == None:
return errors.not_provided()
else:
if self.checkURL(val[i]['URL']) == errors.check_link():
check.append(val[i]['URL'])
elif self.checkURL(val[i]['URL']) == errors.broken_url():
broken.append(val[i]['URL'])
elif self.checkURL(val[i]['URL']) == errors.http():
http.append(val[i]['URL'])
elif self.checkURL(val[i]['URL']) == errors.ftp():
ftp.append(val[i]['URL'])
elif self.checkURL(val[i]['URL']) == errors.okay():
okay.append(val[i]['URL'])
if len(check) > 0:
error += errors.check_link() + '\n' + '\n'.join(check)
if len(broken) > 0:
error += errors.broken_url() + '\n' + '\n'.join(check)
if len(http) > 0:
error += errors.http() + '\n' + '\n'.join(check)
if len(ftp) > 0:
error += errors.ftp() + '\n' + '\n'.join(check)
if len(okay) > 0 and (len(check) == 0 or len(broken) == 0
or len(http) == 0 or len(ftp) == 0):
error += errors.okay()
return error
def checkOnlineResourceType(self, val, length):
#print("Input of checkOnlineResourceType() is ...")
ResourcesTypes = list()
response = requests.get(ResourcesTypeURL).text.split('\n')
data = csv.reader(response)
next(data) # Skip the first two row information
next(data)
for item in data:
ResourcesTypes += item[0:1]
ResourcesTypes = list(set(ResourcesTypes))
UmmEnumTypes = self.enums['RelatedUrlTypeEnum']
UmmEnumTypes.extend(self.enums['RelatedURLSubTypeEnum'])
listA = [
"THREDDS CATALOG", "THREDDS DATA", "THREDDS DIRECTORY",
"GET WEB MAP FOR TIME SERIES", "GET RELATED VISUALIZATION",
"GIOVANNI", "WORLDVIEW", "GET MAP SERVICE"
]
listB = [
"GET WEB MAP SERVICE (WMS)", "GET WEB COVERAGE SERVICE (WCS)",
"OPENDAP DATA (DODS)"
]
Results = [[], [], [], [], []]
if length == 1:
val = [val]
for v in val:
try:
t = v['Type']
if t in listA:
Results[1].append(t)
elif t in listB:
Results[2].append(t)
elif t in UmmEnumTypes:
Results[3].append(t)
else:
Results[4].append(t)
except Exception as e:
return "Each Online Resource URL must be accompanied by a URL Type. Valid values can be found in the UMM-Common schema. A type may be selected from either the URL Type enum or the URL Subtype enum. https://git.earthdata.nasa.gov/projects/EMFD/repos/unified-metadata-model/browse/v1.10/umm-cmn-json-schema.json"
if Results[4]:
return "Invalid URL Types: " + "; ".join(
Results[4]
) + "\nA valid type may be selected from either the URL Type enum or the URL Subtype enum. https://git.earthdata.nasa.gov/projects/EMFD/repos/unified-metadata-model/browse/v1.10/umm-cmn-json-schema.json"
# result = "; ".join(['; '.join(r) for r in Results[1:3] if r])
elif Results[2]:
return "OK - two points for data accessability score for providing an advanced service for visualization, subsetting or aggregation which also meets common framework requirements for standard API based data access."
elif Results[1]:
return "OK - one point for data accessability score for providing an advanced service for visualization, subsetting or aggregation"
elif Results[0]:
return errors.okay()
else:
return errors.not_provided()
def checkCampaignShortName(self, val, campaignNum):
#print("Input of checkCampaignShortName() is ...")
CampaignKeys = list()
CampaignLongNames = list()
response = requests.get(ProjectURL).text.split('\n')
data = csv.reader(response)
next(data) # Skip the first two line information
next(data)
for item in data:
if len(item) != 0:
CampaignKeys += item[1:2]
CampaignLongNames += item[2:3]
CampaignKeys = list(set(CampaignKeys))
CampaignLongNames = list(set(CampaignLongNames))
if campaignNum == 1:
if val == None:
return errors.not_provided()
elif val not in CampaignKeys:
if val in CampaignLongNames:
return val + ": incorrect keyword order"
else:
return "The keyword does not conform to GCMD."
else:
return errors.okay()
else:
for i in range(campaignNum):
if val[i]['Campaign']['ShortName'] == None:
return errors.not_provided()
elif val[i]['Campaign']['ShortName'] not in CampaignKeys:
if val[i]['Campaign']['ShortName'] in CampaignLongNames:
return val[i]['Campaign'][
'ShortName'] + ": incorrect keyword order"
else:
return "The keyword does not conform to GCMD."
else:
return errors.okay()
def checkInsertTime(self, val):
#print("Input of checkInsertTime() is " + val)
try:
if val == None:
return errors.not_provided()
if not val.endswith("Z"):
return "InsertTime error."
val = val.replace("Z", "")
t_record = datetime.strptime(val, '%Y-%m-%dT%H:%M:%S')
if t_record.microsecond / 1000 > 999:
return "InsertTime error."
t_now = datetime.now()
if t_record.year > t_now.year:
return "InsertTime error."
return errors.okay()
except ValueError:
return "InsertTime error."
def checkLastUpdate(self, updateTime, prodTime):
#print("Input of checkLastUpdate() is " + updateTime + ', ' + prodTime)
try:
if updateTime == None:
return errors.not_provided()
elif not updateTime.endswith("Z"):
return "LastUpdate time error."
updateTime = updateTime.replace("Z", "")
t_record = datetime.strptime(updateTime, '%Y-%m-%dT%H:%M:%S')
prodTime = prodTime.replace("Z", "")
p_record = datetime.strptime(prodTime, '%Y-%m-%dT%H:%M:%S')
if t_record.microsecond / 1000 > 999:
return "LastUpdate time error."
t_now = datetime.now()
if t_record.year > t_now.year or t_record < p_record:
return "LastUpdate time error."
return errors.okay()
except ValueError:
return "LastUpdate time error."
def checkGranuleUR(self, val):
#print("Input of checkGranuleUR() is " + val)
if val == None:
return "Provide a granule UR for this granule. This is a required field."
else:
return errors.okay()