def Test_get_datasource_descr(self):
datasource_descr = querydb.get_datasource_descr(source_type='EUMETCAST',
source_id='EO:EUM:DAT:SPOT:S10NDVI')
logger.info("Eumetcast source description is: %s", datasource_descr)
for row in datasource_descr:
print row
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id='USGS:EARLWRN:FEWSNET')
logger.info("Internet source description is: %s", datasource_descr)
for row in datasource_descr:
print row
self.assertEqual(1, 1)
def Test_get_datasource_descr(self):
datasource_descr = querydb.get_datasource_descr(source_type='EUMETCAST',
source_id='EO:EUM:DAT:SPOT:S10NDVI')
logger.info("Eumetcast source description is: %s", datasource_descr)
for row in datasource_descr:
print row
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id='USGS:EARLWRN:FEWSNET')
logger.info("Internet source description is: %s", datasource_descr)
for row in datasource_descr:
print row
self.assertEqual(1, 1)
def ingest_netcdf_cds(internet_source, downloaded_file, processed_item):
ingestion_status = False
try:
product = {
"productcode": internet_source.productcode,
"version": internet_source.version
}
# Datasource description
datasource_descr = querydb.get_datasource_descr(
source_type='INTERNET', source_id=internet_source.internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
sub_datasource = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
ingestion_status = ingestion_netcdf.ingestion_netcdf(
downloaded_file,
processed_item.split(':')[0], product, sub_datasource,
datasource_descr, logger)
except Exception as inst:
logger.debug("Error in CDS Ingestion: %s" % internet_source)
raise
return ingestion_status
def ingest_jrc_wbd(input_dir, in_date=None, avg=None):
if avg:
date_fileslist = glob.glob(input_dir + '/JRC-WBD_AVG2000-' + in_date +
'*')
subproductcode = 'avg'
mapsetcode = 'WD-GEE-ECOWAS-AVG'
datasource_descrID = 'JRC:WBD:GEE:AVG'
else:
date_fileslist = glob.glob(input_dir + '/JRC-WBD_' + in_date + '*')
subproductcode = 'occurr'
mapsetcode = 'WD-GEE-ECOWAS-1'
datasource_descrID = 'JRC:WBD:GEE'
productcode = 'wd-gee'
productversion = '1.0'
product = {"productcode": productcode, "version": productversion}
args = {
"productcode": productcode,
"subproductcode": subproductcode,
"datasource_descr_id": datasource_descrID,
"version": productversion
}
product_in_info = querydb.get_product_in_info(**args)
re_process = product_in_info.re_process
re_extract = product_in_info.re_extract
sprod = {
'subproduct': subproductcode,
'mapsetcode': mapsetcode,
're_extract': re_extract,
're_process': re_process
}
subproducts = []
subproducts.append(sprod)
output_file = es_constants.es2globals['processing_dir']+\
functions.set_path_sub_directory(productcode, subproductcode, 'Ingest', productversion, mapsetcode) +\
functions.set_path_filename(in_date,productcode,subproductcode,mapsetcode,productversion,'.tif')
for internet_filter, datasource_descr in querydb.get_datasource_descr(
source_type='INTERNET', source_id=datasource_descrID):
ingestion.ingestion(date_fileslist,
in_date,
product,
subproducts,
datasource_descr,
logger,
echo_query=1)
return output_file
def test_ingest_g_cls_ndvi_200_1Km(self):
# Test Copernicus Products version 2.2 (starting with NDVI 2.2.1)
productcode = 'vgt-ndvi'
productversion = 'proba-v2.2'
subproductcode = 'ndv'
mapsetcode = 'SPOTV-Africa-1km'
datasource_descrID = 'PDF:GLS:PROBA-V1:NDVI300'
# input_dir = self.test_ingest_dir + os.path.sep + productcode + os.path.sep + self.native_dir
#date_fileslist = [os.path.join(input_dir, 'c_gls_NDVI_202003010000_AFRI_PROBAV_V2.2.1.zip')]
date_fileslist = glob.glob(
'/eos/jeodpp/home/users/venkavi/data/processing/vgt-ndvi/sv2-pv2.2/archive/c_gls_NDVI300_202007110000_GLOBE_PROBAV_V1.0.1.nc*'
)
in_date = '202007110000'
out_date = '20200711'
product = {"productcode": productcode, "version": productversion}
args = {
"productcode": productcode,
"subproductcode": subproductcode,
"datasource_descr_id": datasource_descrID,
"version": productversion
}
product_in_info = querydb.get_product_in_info(**args)
re_process = product_in_info.re_process
re_extract = product_in_info.re_extract
sprod = {
'subproduct': subproductcode,
'mapsetcode': mapsetcode,
're_extract': re_extract,
're_process': re_process
}
subproducts = [sprod]
# Remove existing output
# self.remove_output_file(productcode, subproductcode, productversion, mapsetcode, out_date)
datasource_descr = querydb.get_datasource_descr(
source_type='INTERNET', source_id=datasource_descrID)
ingestion.ingestion(date_fileslist,
in_date,
product,
subproducts,
datasource_descr[0],
logger,
echo_query=1,
test_mode=False)
# status = self.checkIngestedFile(productcode=productcode, subproductcode=subproductcode,
# version=productversion, mapsetcode=mapsetcode, date=out_date)
self.assertEqual(1, 1)
def debug_CDS_MSLP_hour_netcdf(self):
internet_id = "CDS:ERA5:REANALYSIS:MSLP:HOUR"
product = {"productcode": "era5-hourly-mslp", "version": "1.0"}
downloaded_file = '/data/processing/era5-hourly-mslp/1.0/archive/202101010100_reanalysis-era5-single-levels_reanalysis_mean_sea_level_pressure.nc'
in_date = '202101010000'
# Datasource description
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id=internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
sub_datasource = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
ingestion_status = ingestion_netcdf.ingestion_netcdf(downloaded_file,
in_date,
product,
sub_datasource,
datasource_descr,
logger,
test_mode=True)
def debug_CDS_SST_MONTH_netcdf(self):
internet_id = "CDS:ERA5:REANALYSIS:SST:MONTH"
product = {"productcode": "era5-monthly-sst", "version": "1.0"}
downloaded_file = '/data/ingest/20210101_sst_monthly_average.nc'
in_date = '202101010000'
# Datasource description
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id=internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
sub_datasource = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
ingestion_status = ingestion_netcdf.ingestion_netcdf(downloaded_file,
in_date,
product,
sub_datasource,
datasource_descr,
logger,
test_mode=True)
def debug_IRI_PRCP_1Month_ingest_netcdf(self):
internet_id = "IRI:NOAA:PRCP:MONTH" #'CDS:ERA5:REANALYSIS:SST:MONTH'
product = {"productcode": "iri_prcp", "version": "1.0"}
downloaded_file = '/data/processing/iri_prcp/1.0/archive/20210101-iri_prcp.nc'
in_date = '20210101'
# Datasource description
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id=internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
sub_datasource = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
ingestion_status = ingestion_netcdf.ingestion_netcdf(downloaded_file,
in_date,
product,
sub_datasource,
datasource_descr,
logger,
test_mode=True)
def debug_CDS_RFE_DAY_netcdf(self):
internet_id = "CDS:ERA5:REANALYSIS:RFE:DAY"
product = {"productcode": "era5-rfe", "version": "1.0"}
downloaded_file = '/data/ingest/202103200000_reanalysis-era5-single-levels_reanalysis_total_precipitation.nc'
in_date = '202103200000'
# Datasource description
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id=internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
sub_datasource = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
ingestion_status = ingestion_netcdf.ingestion_netcdf(downloaded_file,
in_date,
product,
sub_datasource,
datasource_descr,
logger,
test_mode=True)
def debug_IRI_surfacetemp_1Month_ingest_netcdf(self):
internet_id = "IRI:NOAA:SURFACETEMP:MONTH" #'CDS:ERA5:REANALYSIS:SST:MONTH'
product = {"productcode": "iri-surface-temp", "version": "1.0"}
downloaded_file = '/tmp/climatestation/surface_temp_Jan_2020.nc'
in_date = '20200101'
# Datasource description
datasource_descr = querydb.get_datasource_descr(source_type='INTERNET',
source_id=internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
sub_datasource = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
ingestion_status = ingestion_netcdf.ingestion_netcdf(downloaded_file,
in_date,
product,
sub_datasource,
datasource_descr,
logger,
test_mode=True)
def iri_api_loop_internet(internet_source):
logger_spec = log.my_logger('apps.get_datastore.' +
internet_source.internet_id)
if internet_source.user_name is None:
user_name = "anonymous"
else:
user_name = internet_source.user_name
if internet_source.password is None:
password = "******"
else:
password = internet_source.password
usr_pwd = str(user_name) + ':' + str(password)
# Create the full filename from a 'template' which contains
internet_url = str(internet_source.url)
# processed_list = []
# processed_list_filename = es_constants.get_datastore_processed_list_prefix + internet_source.internet_id.replace(":", "_") + '.list'
# processed_list = functions.restore_obj_from_json(processed_list,
# processed_list_filename)
try:
# Check if template is dict or string them create resources_parameters
# if type(template_paramater) is dict:
# resources_parameters = template_paramater
# else:
# resources_parameters = json.loads(template_paramater)
if internet_source.productcode is None or internet_source.version is None:
logger.error("Product is not passed")
return
product = {
"productcode": internet_source.productcode,
"version": internet_source.version
}
# Datasource description
datasource_descr = querydb.get_datasource_descr(
source_type='INTERNET', source_id=internet_source.internet_id)
datasource_descr = datasource_descr[0]
# Get list of subproducts
subproducts = ingestion.get_subrproducts_from_ingestion(
product, datasource_descr.datasource_descr_id)
dates = build_list_dates_generic(from_date=internet_source.start_date,
to_date=internet_source.end_date,
frequency_id=str(
internet_source.frequency_id))
# Dates defined are dynamic not based on the configuration file
iri_api.process_list_matching_url(datasource_descr, product,
subproducts, dates)
# functions.dump_obj_to_json(processed_list, processed_list_filename)
except:
logger.error("Error in IRI datastore service. Continue")
b_error = True
finally:
logger.info("IRI datastore service Ending")
current_list = []
return current_list
def loop_ingestion_drive(dry_run=False, test_one_product=None):
echo_query = False
# Get all active product ingestion records with a subproduct count.
active_product_ingestions = querydb.get_ingestion_product(allrecs=True)
for active_product_ingest in active_product_ingestions:
productcode = active_product_ingest[0]
productversion = active_product_ingest[1]
# Verify the test-one-product case
do_ingest_product = is_test_one_product(test_one_product, productcode)
if do_ingest_product:
logger.info("Ingestion active for product: [%s] subproduct N. %s" %
(active_product_ingest[0], active_product_ingest[2]))
# For the current active product ingestion: get all
product = {"productcode": productcode, "version": productversion}
logger.debug("Processing product: %s - version %s" %
(productcode, productversion))
# Get the list of acquisition sources that are defined for this ingestion 'trigger'
# (i.e. prod/version)
# NOTE: the following implies there is 1 and only 1 '_native' subproduct associated to a 'product';
native_product = {
"productcode": productcode,
"subproductcode": productcode + "_native",
"version": productversion
}
sources_list = querydb.get_product_sources(**native_product)
logger.debug("For product [%s] N. %s source is/are found" %
(productcode, len(sources_list)))
systemsettings = functions.getSystemSettings()
for source in sources_list:
logger_spec = log.my_logger('apps.ingestion.' + productcode +
'.' + productversion)
logger.debug("Processing Source type [%s] with id [%s]" %
(source.type, source.data_source_id))
# Re-initialize the datasource_descr
# datasource_descr = None
# Get datasource desctiption
datasource_descr = querydb.get_datasource_descr(
source_type=source.type, source_id=source.data_source_id)
datasource_descr = datasource_descr[0]
# TODO optimize this in order to get direct file filter expression
my_filter_expr = get_filenaming_info(source, datasource_descr)
files = get_files_matching_with_file_expression(my_filter_expr)
# See ES2-204
logger_spec.debug(
"Number of files found for product [%s] is: %s" %
(active_product_ingest[0], len(files)))
if len(files) > 0:
# Get list of ingestions triggers [prod/subprod/mapset]
ingestions = querydb.get_ingestion_subproduct(
allrecs=False, **product)
# Loop over ingestion triggers
subproducts = list()
for ingest in ingestions:
# TODO if one ingest gives true and another false?
dates_not_in_filename = is_date_not_in_filename(
ingest.input_to_process_re)
logger.debug(" --> processing subproduct: %s" %
ingest.subproductcode)
args = {
"productcode": product['productcode'],
"subproductcode": ingest.subproductcode,
"datasource_descr_id":
datasource_descr.datasource_descr_id,
"version": product['version']
}
product_in_info = querydb.get_product_in_info(**args)
# TODO verify the approach Should we get subproduct from single query
subproduct = get_subproduct(
ingest, product_in_info,
datasource_descr.datasource_descr_id)
if subproduct is not None:
subproducts.append(subproduct)
if subproducts is None:
#TODO what to do?
logger.error(
"For current active ingestion No subproducts for Product [%s] "
% (productcode))
# Get the list of unique dates by extracting the date from all files.
dates_list = get_list_unique_dates(datasource_descr, files,
dates_not_in_filename,
product_in_info,
ingest.mapsetcode)
# Loop over dates and get list of files
for in_date in dates_list:
date_fileslist = get_dates_file_list(
dates_not_in_filename, files, my_filter_expr,
in_date, logger_spec)
# Pass list of files to ingestion routine
if (not dry_run):
try:
result = ingestion(date_fileslist,
in_date,
product,
subproducts,
datasource_descr,
logger_spec,
echo_query=echo_query)
except:
logger.error(
"Error in ingestion of file [%s] " %
(functions.conv_list_2_string(
date_fileslist)))
else:
# Result is None means we are still waiting for some files to be received. Keep files in /data/ingest
# dates_not_in_filename means the input files contains many dates (e.g. GSOD precip)
if result is not None and not dates_not_in_filename:
if source.store_original_data or systemsettings[
'type_installation'] == 'Server':
store_native_files(
product, date_fileslist,
logger_spec)
else:
delete_files(date_fileslist,
logger_spec)
else:
time.sleep(10)
