def handle(self, *args, **options):
logger = logging.getLogger(__name__)
resource_counter = 0
to_resource_type = 'CompositeResource'
msg = "THERE ARE CURRENTLY {} GENERIC RESOURCES PRIOR TO CONVERSION.".format(
GenericResource.objects.all().count())
logger.info(msg)
print(">> {}".format(msg))
for gen_res in GenericResource.objects.all():
# change the resource_type
gen_res.resource_type = to_resource_type
gen_res.content_model = to_resource_type.lower()
gen_res.save()
# get the converted resource object - CompositeResource
comp_res = gen_res.get_content_model()
# update url attribute of the metadata 'type' element
type_element = comp_res.metadata.type
type_element.url = '{0}/terms/{1}'.format(current_site_url(), to_resource_type)
type_element.save()
# set resource to dirty so that resource level xml files (resource map and
# metadata xml files) will be generated as part of next bag download
set_dirty_bag_flag(comp_res)
resource_counter += 1
msg = "{} GENERIC RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE.".format(
resource_counter)
logger.info(msg)
print(">> {}".format(msg))
msg = "THERE ARE CURRENTLY {} GENERIC RESOURCES AFTER CONVERSION.".format(
GenericResource.objects.all().count())
logger.info(msg)
print(">> {}".format(msg))
def handle(self, *args, **options):
logger = logging.getLogger(__name__)
resource_counter = 0
to_resource_type = 'CompositeResource'
msg = "THERE ARE CURRENTLY {} MULTIDIMENSIONAL RESOURCES PRIOR TO CONVERSION.".format(
NetcdfResource.objects.all().count())
logger.info(msg)
print(">> {}".format(msg))
for nc_res in NetcdfResource.objects.all():
# check resource exists on irods
istorage = nc_res.get_irods_storage()
if not istorage.exists(nc_res.root_path):
err_msg = "NetCDF resource not found in irods (ID: {})".format(
nc_res.short_id)
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
# skip this netcdf resource for migration
continue
# get the nc file name which needs to be used to create a new folder
nc_file = None
txt_file = None
if nc_res.files.count() == 2:
for res_file in nc_res.files.all():
if res_file.extension.lower() == '.nc':
nc_file = res_file
elif res_file.file_name.lower().endswith(
'header_info.txt'):
txt_file = res_file
create_nc_aggregation = nc_file is not None and txt_file is not None
if create_nc_aggregation:
# check resource files exist on irods
file_missing = False
for res_file in nc_res.files.all():
file_path = res_file.public_path
if not istorage.exists(file_path):
err_msg = "File path not found in irods:{}".format(
file_path)
logger.error(err_msg)
err_msg = "Failed to convert netcdf resource (ID: {}). Resource file is " \
"missing on irods".format(nc_res.short_id)
print("Error:>> {}".format(err_msg))
file_missing = True
break
if file_missing:
# skip this corrupt netcdf resource for migration
continue
# change the resource_type
nc_metadata_obj = nc_res.metadata
nc_res.resource_type = to_resource_type
nc_res.content_model = to_resource_type.lower()
nc_res.save()
# get the converted resource object - CompositeResource
comp_res = nc_res.get_content_model()
# set CoreMetaData object for the composite resource
core_meta_obj = CoreMetaData.objects.create()
comp_res.content_object = core_meta_obj
# migrate netcdf resource core metadata elements to composite resource
migrate_core_meta_elements(nc_metadata_obj, comp_res)
# update url attribute of the metadata 'type' element
type_element = comp_res.metadata.type
type_element.url = '{0}/terms/{1}'.format(current_site_url(),
to_resource_type)
type_element.save()
if create_nc_aggregation:
# create a NetCDF aggregation
nc_aggr = None
try:
nc_aggr = NetCDFLogicalFile.create(resource=comp_res)
except Exception as ex:
err_msg = 'Failed to create NetCDF aggregation for resource (ID: {})'
err_msg = err_msg.format(nc_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
if nc_aggr is not None:
# set aggregation dataset title
nc_aggr.dataset_name = comp_res.metadata.title.value
nc_aggr.save()
# make the res files part of the aggregation
for res_file in comp_res.files.all():
nc_aggr.add_resource_file(res_file)
# migrate netcdf specific metadata to aggregation
for variable in nc_metadata_obj.variables.all():
variable.content_object = nc_aggr.metadata
variable.save()
# create aggregation level coverage elements
for coverage in comp_res.metadata.coverages.all():
aggr_coverage = Coverage()
aggr_coverage.type = coverage.type
aggr_coverage._value = coverage._value
aggr_coverage.content_object = nc_aggr.metadata
aggr_coverage.save()
org_coverage = nc_metadata_obj.originalCoverage
if org_coverage:
org_coverage.content_object = nc_aggr.metadata
org_coverage.save()
# create aggregation level keywords
keywords = [
sub.value for sub in comp_res.metadata.subjects.all()
]
nc_aggr.metadata.keywords = keywords
# set aggregation metadata dirty status to that of the netcdf resource metadata
# dirty status - this would trigger netcdf file update for the new aggregation
# if metadata is dirty
nc_aggr.metadata.is_dirty = nc_metadata_obj.is_dirty
nc_aggr.metadata.save()
# create aggregation level xml files
nc_aggr.create_aggregation_xml_documents()
msg = 'One Multidimensional aggregation was created in resource (ID: {})'
msg = msg.format(comp_res.short_id)
logger.info(msg)
# set resource to dirty so that resource level xml files (resource map and
# metadata xml files) will be re-generated as part of next bag download
comp_res.save()
try:
set_dirty_bag_flag(comp_res)
except Exception as ex:
err_msg = 'Failed to set bag flag dirty for the converted resource (ID: {})'
err_msg = err_msg.format(nc_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
resource_counter += 1
# delete the instance of NetCdfMetaData that was part of the original netcdf resource
nc_metadata_obj.delete()
msg = 'Multidimensional resource (ID: {}) was converted to Composite Resource type'
msg = msg.format(comp_res.short_id)
logger.info(msg)
msg = "{} MULTIDIMENSIONAL RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE.".format(
resource_counter)
logger.info(msg)
print(">> {}".format(msg))
msg = "THERE ARE CURRENTLY {} MULTIDIMENSIONAL RESOURCES AFTER CONVERSION.".format(
NetcdfResource.objects.all().count())
logger.info(msg)
if NetcdfResource.objects.all().count() > 0:
msg = "NOT ALL MULTIDIMENSIONAL RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE TYPE"
logger.error(msg)
print(">> {}".format(msg))
def handle(self, *args, **options):
logger = logging.getLogger(__name__)
resource_counter = 0
to_resource_type = 'CompositeResource'
msg = "THERE ARE CURRENTLY {} GEOFEATURE RESOURCES PRIOR TO CONVERSION.".format(
GeographicFeatureResource.objects.all().count())
logger.info(msg)
print(">> {}".format(msg))
for gf_res in GeographicFeatureResource.objects.all():
# check resource exists on irods
istorage = gf_res.get_irods_storage()
if not istorage.exists(gf_res.root_path):
err_msg = "Geofeature resource not found in irods (ID: {})".format(
gf_res.short_id)
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
# skip this geofeature resource for migration
continue
create_gf_aggregation = False
if gf_res.has_required_content_files() and \
gf_res.metadata.geometryinformation is not None:
create_gf_aggregation = True
if create_gf_aggregation:
# check resource files exist on irods
file_missing = False
for res_file in gf_res.files.all():
file_path = res_file.public_path
if not istorage.exists(file_path):
err_msg = "File path not found in irods:{}".format(
file_path)
logger.error(err_msg)
err_msg = "Failed to convert geofeature resource (ID: {}). " \
"Resource file is missing on irods"
err_msg = err_msg.format(gf_res.short_id)
print("Error:>> {}".format(err_msg))
file_missing = True
break
if file_missing:
# skip this corrupt geofeature resource for migration
continue
# change the resource_type
gf_metadata_obj = gf_res.metadata
gf_res.resource_type = to_resource_type
gf_res.content_model = to_resource_type.lower()
gf_res.save()
# get the converted resource object - CompositeResource
comp_res = gf_res.get_content_model()
# set CoreMetaData object for the composite resource
core_meta_obj = CoreMetaData.objects.create()
comp_res.content_object = core_meta_obj
# migrate geofeature resource core metadata elements to composite resource
migrate_core_meta_elements(gf_metadata_obj, comp_res)
# update url attribute of the metadata 'type' element
type_element = comp_res.metadata.type
type_element.url = '{0}/terms/{1}'.format(current_site_url(),
to_resource_type)
type_element.save()
if create_gf_aggregation:
# create a Geofeature aggregation
gf_aggr = None
try:
gf_aggr = GeoFeatureLogicalFile.create(resource=comp_res)
except Exception as ex:
err_msg = 'Failed to create Geofeature aggregation for resource (ID: {})'
err_msg = err_msg.format(gf_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
if gf_aggr is not None:
# set aggregation dataset title
gf_aggr.dataset_name = comp_res.metadata.title.value
gf_aggr.save()
# make the res files part of the aggregation
for res_file in comp_res.files.all():
gf_aggr.add_resource_file(res_file)
# migrate geofeature specific metadata to aggregation
for fieldinfo in gf_metadata_obj.fieldinformations.all():
fieldinfo.content_object = gf_aggr.metadata
fieldinfo.save()
# create aggregation level coverage elements
for coverage in comp_res.metadata.coverages.all():
aggr_coverage = Coverage()
aggr_coverage.type = coverage.type
aggr_coverage._value = coverage._value
aggr_coverage.content_object = gf_aggr.metadata
aggr_coverage.save()
org_coverage = gf_metadata_obj.originalcoverage
if org_coverage:
org_coverage.content_object = gf_aggr.metadata
org_coverage.save()
geom_info = gf_metadata_obj.geometryinformation
if geom_info:
geom_info.content_object = gf_aggr.metadata
geom_info.save()
# create aggregation level keywords
keywords = [
sub.value for sub in comp_res.metadata.subjects.all()
]
gf_aggr.metadata.keywords = keywords
# create aggregation level xml files
gf_aggr.create_aggregation_xml_documents()
msg = 'One Geofeature aggregation was created in resource (ID: {})'
msg = msg.format(comp_res.short_id)
logger.info(msg)
comp_res.save()
# set resource to dirty so that resource level xml files (resource map and
# metadata xml files) will be re-generated as part of next bag download
try:
set_dirty_bag_flag(comp_res)
except Exception as ex:
err_msg = 'Failed to set bag flag dirty for the converted resource (ID: {})'
err_msg = err_msg.format(gf_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
resource_counter += 1
# delete the instance of GeographicFeatureMetaData that was part of the original
# geofeature resource
gf_metadata_obj.delete()
msg = 'Geofeature resource (ID: {}) was converted to Composite Resource type'
msg = msg.format(comp_res.short_id)
logger.info(msg)
msg = "{} GEOFEATURE RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE.".format(
resource_counter)
logger.info(msg)
print(">> {}".format(msg))
msg = "THERE ARE CURRENTLY {} GEOFEATURE RESOURCES AFTER CONVERSION.".format(
GeographicFeatureResource.objects.all().count())
logger.info(msg)
if GeographicFeatureResource.objects.all().count() > 0:
msg = "NOT ALL GEOFEATURE RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE TYPE"
logger.error(msg)
print(">> {}".format(msg))
def normalize_metadata(metadata_str):
"""Prepares metadata string to match resource id and hydroshare url of original"""
return metadata_str\
.replace(current_site_url(), "http://www.hydroshare.org")\
.replace(res.short_id, "97523bdb7b174901b3fc2d89813458f1")
def handle(self, *args, **options):
logger = logging.getLogger(__name__)
resource_counter = 0
create_raster_aggregation = False
to_resource_type = 'CompositeResource'
msg = "THERE ARE CURRENTLY {} RASTER RESOURCES PRIOR TO CONVERSION.".format(
RasterResource.objects.all().count())
logger.info(msg)
print(">> {}".format(msg))
for rast_res in RasterResource.objects.all():
# check resource exists on irods
istorage = rast_res.get_irods_storage()
create_raster_aggregation = False
if not istorage.exists(rast_res.root_path):
err_msg = "Raster resource not found in irods (ID: {})".format(rast_res.short_id)
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
# skip this raster resource
continue
if rast_res.metadata.cellInformation is not None:
# get the vrt file name which needs to be used to create a new folder for
# raster aggregation
vrt_file = None
for res_file in rast_res.files.all():
if res_file.extension.lower() == '.vrt':
vrt_file = res_file
break
create_raster_aggregation = vrt_file is not None
if create_raster_aggregation:
# check resource files exist on irods
file_missing = False
for res_file in rast_res.files.all():
file_path = res_file.public_path
if not istorage.exists(file_path):
err_msg = "File path not found in irods:{}".format(file_path)
logger.error(err_msg)
err_msg = "Failed to convert raster resource (ID: {}). " \
"Resource file is missing on irods".format(rast_res.short_id)
print("Error:>> {}".format(err_msg))
file_missing = True
break
if file_missing:
# skip this corrupt raster resource for migration
continue
# change the resource_type
ras_metadata_obj = rast_res.metadata
rast_res.resource_type = to_resource_type
rast_res.content_model = to_resource_type.lower()
rast_res.save()
# get the converted resource object - CompositeResource
comp_res = rast_res.get_content_model()
# set CoreMetaData object for the composite resource
core_meta_obj = CoreMetaData.objects.create()
comp_res.content_object = core_meta_obj
# migrate raster resource core metadata elements to composite resource
migrate_core_meta_elements(ras_metadata_obj, comp_res)
# update url attribute of the metadata 'type' element
type_element = comp_res.metadata.type
type_element.url = '{0}/terms/{1}'.format(current_site_url(), to_resource_type)
type_element.save()
if create_raster_aggregation:
# create a Raster aggregation
ras_aggr = None
try:
ras_aggr = GeoRasterLogicalFile.create(resource=comp_res)
except Exception as ex:
err_msg = 'Failed to create raster aggregation for resource (ID: {})'
err_msg = err_msg.format(rast_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
if ras_aggr is not None:
# set aggregation dataset title
ras_aggr.dataset_name = comp_res.metadata.title.value
ras_aggr.save()
# make the res files part of the aggregation
for res_file in comp_res.files.all():
ras_aggr.add_resource_file(res_file)
# migrate raster specific metadata to aggregation
for bandinfo in ras_metadata_obj.bandInformations:
bandinfo.content_object = ras_aggr.metadata
bandinfo.save()
# create aggregation level spatial coverage element
# note - the resource level spatial coverage which is a core metadata
# element gets populated as part of raster resource creation
spatial_coverage = comp_res.metadata.spatial_coverage
if spatial_coverage:
aggr_coverage = Coverage()
aggr_coverage.type = spatial_coverage.type
aggr_coverage._value = spatial_coverage._value
aggr_coverage.content_object = ras_aggr.metadata
aggr_coverage.save()
org_coverage = ras_metadata_obj.originalCoverage
if org_coverage:
org_coverage.content_object = ras_aggr.metadata
org_coverage.save()
cell_info = ras_metadata_obj.cellInformation
if cell_info:
cell_info.content_object = ras_aggr.metadata
cell_info.save()
# create aggregation level xml files
ras_aggr.create_aggregation_xml_documents()
msg = 'One Raster aggregation was created in resource (ID: {})'
msg = msg.format(comp_res.short_id)
logger.info(msg)
# set resource to dirty so that resource level xml files (resource map and
# metadata xml files) will be re-generated as part of next bag download
comp_res.save()
try:
set_dirty_bag_flag(comp_res)
except Exception as ex:
err_msg = 'Failed to set bag flag dirty for the converted resource (ID: {})'
err_msg = err_msg.format(rast_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
resource_counter += 1
# delete the instance of RasterMetaData that was part of the original raster resource
ras_metadata_obj.delete()
msg = 'Raster resource (ID: {}) was converted to Composite Resource type'
msg = msg.format(comp_res.short_id)
logger.info(msg)
msg = "{} RASTER RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE.".format(
resource_counter)
logger.info(msg)
print(">> {}".format(msg))
msg = "THERE ARE CURRENTLY {} RASTER RESOURCES AFTER CONVERSION.".format(
RasterResource.objects.all().count())
logger.info(msg)
if RasterResource.objects.all().count() > 0:
msg = "NOT ALL RASTER RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE TYPE"
logger.error(msg)
print(">> {}".format(msg))
def handle(self, *args, **options):
logger = logging.getLogger(__name__)
resource_counter = 0
to_resource_type = 'CompositeResource'
msg = "THERE ARE CURRENTLY {} TIMESERIES RESOURCES PRIOR TO CONVERSION.".format(
TimeSeriesResource.objects.all().count())
logger.info(msg)
print(">> {}".format(msg))
for ts_res in TimeSeriesResource.objects.all():
# check resource exists on irods
istorage = ts_res.get_irods_storage()
if not istorage.exists(ts_res.root_path):
err_msg = "Timeseries resource not found in irods (ID: {})".format(
ts_res.short_id)
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
# skip this timeseries resource for migration
continue
sqlite_file = None
res_file_count = ts_res.files.count()
if res_file_count == 1 or res_file_count == 2:
for res_file in ts_res.files.all():
if res_file.extension.lower() == '.sqlite':
sqlite_file = res_file
create_ts_aggregation = sqlite_file is not None
if create_ts_aggregation:
# check resource files exist on irods
file_missing = False
for res_file in ts_res.files.all():
file_path = res_file.public_path
if not istorage.exists(file_path):
err_msg = "File path not found in irods:{}".format(
file_path)
logger.error(err_msg)
err_msg = "Failed to convert timeseries resource (ID: {}). " \
"Resource file is missing on irods".format(ts_res.short_id)
print("Error:>> {}".format(err_msg))
file_missing = True
break
if file_missing:
# skip this corrupt timeseries resource for migration
continue
# change the resource_type
ts_metadata_obj = ts_res.metadata
ts_res.resource_type = to_resource_type
ts_res.content_model = to_resource_type.lower()
ts_res.save()
# get the converted resource object - CompositeResource
comp_res = ts_res.get_content_model()
# set CoreMetaData object for the composite resource
core_meta_obj = CoreMetaData.objects.create()
comp_res.content_object = core_meta_obj
# migrate timeseries resource core metadata elements to composite resource
migrate_core_meta_elements(ts_metadata_obj, comp_res)
# update url attribute of the metadata 'type' element
type_element = comp_res.metadata.type
type_element.url = '{0}/terms/{1}'.format(current_site_url(),
to_resource_type)
type_element.save()
if create_ts_aggregation:
# create a Timeseries aggregation
ts_aggr = None
try:
ts_aggr = TimeSeriesLogicalFile.create(resource=comp_res)
except Exception as ex:
err_msg = 'Failed to create Timeseries aggregation for resource (ID: {})'
err_msg = err_msg.format(ts_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
if ts_aggr is not None:
# set aggregation dataset title
ts_aggr.dataset_name = comp_res.metadata.title.value
ts_aggr.save()
# make the res files part of the aggregation
for res_file in comp_res.files.all():
ts_aggr.add_resource_file(res_file)
# migrate timeseries specific metadata to aggregation
for site in ts_metadata_obj.sites:
site.content_object = ts_aggr.metadata
site.save()
for variable in ts_metadata_obj.variables:
variable.content_object = ts_aggr.metadata
variable.save()
for method in ts_metadata_obj.methods:
method.content_object = ts_aggr.metadata
method.save()
for proc_level in ts_metadata_obj.processing_levels:
proc_level.content_object = ts_aggr.metadata
proc_level.save()
for ts_result in ts_metadata_obj.time_series_results:
ts_result.content_object = ts_aggr.metadata
ts_result.save()
# create aggregation level coverage elements
for coverage in comp_res.metadata.coverages.all():
aggr_coverage = Coverage()
aggr_coverage.type = coverage.type
aggr_coverage._value = coverage._value
aggr_coverage.content_object = ts_aggr.metadata
aggr_coverage.save()
utc_offset = ts_metadata_obj.utc_offset
if utc_offset:
utc_offset.content_object = ts_aggr.metadata
utc_offset.save()
ts_aggr.metadata.value_counts = ts_metadata_obj.value_counts
ts_aggr.metadata.save()
# create aggregation level keywords
keywords = [
sub.value for sub in comp_res.metadata.subjects.all()
]
ts_aggr.metadata.keywords = keywords
# set aggregation metadata dirty status to that of the timeseries resource
# metadata dirty status - this would trigger netcdf file update for the
# new aggregation if metadata is dirty
ts_aggr.metadata.is_dirty = ts_metadata_obj.is_dirty
ts_aggr.metadata.save()
# create aggregation level xml files
ts_aggr.create_aggregation_xml_documents()
msg = 'One Timeseries aggregation was created in resource (ID: {})'
msg = msg.format(comp_res.short_id)
logger.info(msg)
comp_res.save()
# set resource to dirty so that resource level xml files (resource map and
# metadata xml files) will be re-generated as part of next bag download
try:
set_dirty_bag_flag(comp_res)
except Exception as ex:
err_msg = 'Failed to set bag flag dirty for the converted resource (ID: {})'
err_msg = err_msg.format(ts_res.short_id)
err_msg = err_msg + '\n' + ex.message
logger.error(err_msg)
print("Error:>> {}".format(err_msg))
resource_counter += 1
# delete the instance of TimeSeriesMetaData that was part of the original
# timeseries resource
ts_metadata_obj.delete()
msg = 'Timeseries resource (ID: {}) was converted to Composite Resource type'
msg = msg.format(comp_res.short_id)
logger.info(msg)
msg = "{} TIMESERIES RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE.".format(
resource_counter)
logger.info(msg)
print(">> {}".format(msg))
msg = "THERE ARE CURRENTLY {} TIMESERIES RESOURCES AFTER CONVERSION.".format(
TimeSeriesResource.objects.all().count())
logger.info(msg)
if TimeSeriesResource.objects.all().count() > 0:
msg = "NOT ALL TIMESERIES RESOURCES WERE CONVERTED TO COMPOSITE RESOURCE TYPE"
logger.error(msg)
print(">> {}".format(msg))