def test_harvest_error_bad_xml(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/error_bad_xml.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
try:
object_ids = harvester.gather_stage(job)
except lxml.etree.XMLSyntaxError:
# this only occurs in debug_exception_mode
pass
else:
assert object_ids is None
# Check gather errors
assert len(job.gather_errors) == 1
assert job.gather_errors[0].harvest_job_id == job.id
assert 'Error parsing the document' in job.gather_errors[0].message
def get_validation_errors(self, validation_test_filename):
'''
:param validation_test_filename:
'''
# Create source
source_fixture = {
u'title': u'Test Source',
u'name': u'test-source',
u'url': u'http://127.0.0.1:8999/gemini2.1/validation/%s' %
validation_test_filename,
u'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
# Gather stage for GeminiDocHarvester includes validation
object_ids = harvester.gather_stage(job)
# Check the validation errors
errors = u'; '.join(
[gather_error.message for gather_error in job.gather_errors])
return errors
def test_harvest_error_bad_xml(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/error_bad_xml.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
try:
object_ids = harvester.gather_stage(job)
except lxml.etree.XMLSyntaxError:
# this only occurs in debug_exception_mode
pass
else:
assert object_ids is None
# Check gather errors
assert len(job.gather_errors) == 1
assert job.gather_errors[0].harvest_job_id == job.id
assert 'Error parsing the document' in job.gather_errors[0].message
def _run_job_for_single_document(self,job,force_import=False,expect_gather_errors=False,expect_obj_errors=False):
harvester = GeminiDocHarvester()
harvester.force_import = force_import
object_ids = harvester.gather_stage(job)
assert object_ids, len(object_ids) == 1
if expect_gather_errors:
assert len(job.gather_errors) > 0
else:
assert len(job.gather_errors) == 0
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
harvester.import_stage(obj)
Session.refresh(obj)
if expect_obj_errors:
assert len(obj.errors) > 0
else:
assert len(obj.errors) == 0
job.status = u'Finished'
job.save()
return obj
def get_validation_errors(self, validation_test_filename):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/validation/%s' % validation_test_filename,
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
# Gather stage for GeminiDocHarvester includes validation
harvester.gather_stage(job)
# Check the validation errors
errors = '; '.join([gather_error.message for gather_error in job.gather_errors])
return errors
def test_harvest_error_validation(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/error_validation.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
# Right now the import process goes ahead even with validation errors
assert object_ids, len(object_ids) == 1
# No gather errors
assert len(job.gather_errors) == 0
# Fetch stage always returns True for Single Doc harvesters
assert harvester.fetch_stage(object_ids) is True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
assert obj.guid == u'test-error-validation-1'
harvester.import_stage(obj)
# Check errors
assert len(obj.errors) == 1
assert obj.errors[0].harvest_object_id == obj.id
message = obj.errors[0].message
assert_in('One email address shall be provided', message)
assert_in("Service type shall be one of 'discovery', 'view', 'download', 'transformation', 'invoke' or 'other' "
"following INSPIRE generic names", message)
assert_in('Limitations on public access code list value shall be \'otherRestrictions\'', message)
assert_in('One organisation name shall be provided', message)
def test_harvest_error_404(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/not_there.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
assert object_ids is None
# Check gather errors
assert len(job.gather_errors) == 1
assert job.gather_errors[0].harvest_job_id == job.id
assert 'Unable to get content for URL' in job.gather_errors[0].message
def test_harvest_error_404(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/not_there.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
assert object_ids is None
# Check gather errors
assert len(job.gather_errors) == 1
assert job.gather_errors[0].harvest_job_id == job.id
assert 'Unable to get content for URL' in job.gather_errors[0].message
def _run_job_for_single_document(self,job,force_import=False,expect_gather_errors=False,expect_obj_errors=False):
harvester = GeminiDocHarvester()
harvester.force_import = force_import
object_ids = harvester.gather_stage(job)
assert object_ids, len(object_ids) == 1
if expect_gather_errors:
assert len(job.gather_errors) > 0
else:
assert len(job.gather_errors) == 0
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
harvester.import_stage(obj)
Session.refresh(obj)
if expect_obj_errors:
assert len(obj.errors) > 0
else:
assert len(obj.errors) == 0
job.status = u'Finished'
job.save()
return obj
def test_harvest_error_validation(self):
''' '''
# Create source
source_fixture = {
u'title': u'Test Source',
u'name': u'test-source',
u'url': u'http://127.0.0.1:8999/gemini2.1/error_validation.xml',
u'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
# Right now the import process goes ahead even with validation errors
assert object_ids, len(object_ids) == 1
# No gather errors
assert len(job.gather_errors) == 0
# Fetch stage always returns True for Single Doc harvesters
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
assert obj.guid == u'test-error-validation-1'
harvester.import_stage(obj)
# Check errors
assert len(obj.errors) == 1
assert obj.errors[0].harvest_object_id == obj.id
message = obj.errors[0].message
assert_in(u'One email address shall be provided', message)
assert_in(
u'Service type shall be one of \'discovery\', \'view\', \'download\', '
u'\'transformation\', \'invoke\' or \'other\' following INSPIRE generic '
u'names', message)
assert_in(
u'Limitations on public access code list value shall be '
u'\'otherRestrictions\'', message)
assert_in(u'One organisation name shall be provided', message)
def test_harvest_fields_dataset(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/dataset1.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
assert object_ids, len(object_ids) == 1
# No gather errors
assert len(job.gather_errors) == 0
# Fetch stage always returns True for Single Doc harvesters
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
assert obj.guid == u'test-dataset-1'
harvester.import_stage(obj)
# No object errors
assert len(obj.errors) == 0
package_dict = get_action('package_show')(self.context,{'id':obj.package_id})
assert package_dict
expected = {
'name': u'country-parks-scotland',
'title': u'Country Parks (Scotland)',
'tags': [{u'name': u'Nature conservation'}],
'notes': u'Parks are set up by Local Authorities to provide open-air recreation facilities close to towns and cities. [edited]'
}
package_dict['tags'] = self.clean_tags(package_dict['tags'])
for key,value in expected.iteritems():
if not package_dict[key] == value:
raise AssertionError('Unexpected value for %s: %s (was expecting %s)' % \
(key, package_dict[key], value))
if config.get('ckan.harvest.auth.profile') == u'publisher':
assert package_dict['groups'] == [self.publisher.id]
expected_extras = {
# Basic
'guid': obj.guid,
'resource-type': u'dataset',
'responsible-party': u'Scottish Natural Heritage (custodian, distributor)',
'access_constraints': u'["Copyright Scottish Natural Heritage"]',
'contact-email': u'*****@*****.**',
'provider':'',
# Spatial
'bbox-east-long': u'0.205857204',
'bbox-north-lat': u'61.06066944',
'bbox-south-lat': u'54.529947158',
'bbox-west-long': u'-8.97114288',
'spatial': u'{"type": "Polygon", "coordinates": [[[0.205857204, 54.529947158], [-8.97114288, 54.529947158], [-8.97114288, 61.06066944], [0.205857204, 61.06066944], [0.205857204, 54.529947158]]]}',
# Other
'coupled-resource': u'[]',
'dataset-reference-date': u'[{"type": "creation", "value": "2004-02"}, {"type": "revision", "value": "2006-07-03"}]',
'frequency-of-update': u'irregular',
'licence': u'["Reference and PSMA Only", "http://www.test.gov.uk/licenseurl"]',
'licence_url': u'http://www.test.gov.uk/licenseurl',
'metadata-date': u'2011-09-23T10:06:08',
'metadata-language': u'eng',
'spatial-reference-system': u'urn:ogc:def:crs:EPSG::27700',
'temporal_coverage-from': u'["1998"]',
'temporal_coverage-to': u'["2010"]',
}
for key, value in expected_extras.iteritems():
extra_value = self.find_extra(package_dict, key)
if extra_value is None:
raise AssertionError('Extra %s not present in package' % key)
if not extra_value == value:
raise AssertionError('Unexpected value for extra %s: %s (was expecting %s)' % \
(key, package_dict['extras'][key], value))
expected_resource = {
'description': 'Test Resource Description',
'format': u'',
'name': 'Test Resource Name',
'resource_locator_function': 'download',
'resource_locator_protocol': 'test-protocol',
'url': u'https://gateway.snh.gov.uk/pls/apex_ddtdb2/f?p=101',
}
resource = package_dict['resources'][0]
for key,value in expected_resource.iteritems():
if not resource[key] == value:
raise AssertionError('Unexpected value in resource for %s: %s (was expecting %s)' % \
(key, resource[key], value))
def test_harvest_fields_service(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/service1.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
assert object_ids, len(object_ids) == 1
# No gather errors
assert len(job.gather_errors) == 0
# Fetch stage always returns True for Single Doc harvesters
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
assert obj.guid == u'test-service-1'
harvester.import_stage(obj)
# No object errors
assert len(obj.errors) == 0
package_dict = get_action('package_show')(self.context,{'id':obj.package_id})
assert package_dict
expected = {
'name': u'one-scotland-address-gazetteer-web-map-service-wms',
'title': u'One Scotland Address Gazetteer Web Map Service (WMS)',
'tags': [{u'name': u'Addresses'}, {u'name': u'Scottish National Gazetteer'}],
'notes': u'This service displays its contents at larger scale than 1:10000. [edited]',
}
package_dict['tags'] = self.clean_tags(package_dict['tags'])
for key,value in expected.iteritems():
if not package_dict[key] == value:
raise AssertionError('Unexpected value for %s: %s (was expecting %s)' % \
(key, package_dict[key], value))
if config.get('ckan.harvest.auth.profile') == u'publisher':
assert package_dict['groups'] == [self.publisher.id]
expected_extras = {
# Basic
'guid': obj.guid,
'UKLP': u'True',
'resource-type': u'service',
'access_constraints': u'["No restriction on public access"]',
'responsible-party': u'The Improvement Service (owner)',
'provider':u'The Improvement Service',
'contact-email': u'*****@*****.**',
# Spatial
'bbox-east-long': u'0.5242365625',
'bbox-north-lat': u'61.0243',
'bbox-south-lat': u'54.4764484375',
'bbox-west-long': u'-9.099786875',
'spatial': u'{"type": "Polygon", "coordinates": [[[0.5242365625, 54.4764484375], [-9.099786875, 54.4764484375], [-9.099786875, 61.0243], [0.5242365625, 61.0243], [0.5242365625, 54.4764484375]]]}',
# Other
'coupled-resource': u'[{"href": ["http://scotgovsdi.edina.ac.uk/srv/en/csw?service=CSW&request=GetRecordById&version=2.0.2&outputSchema=http://www.isotc211.org/2005/gmd&elementSetName=full&id=250ea276-48e2-4189-8a89-fcc4ca92d652"], "uuid": ["250ea276-48e2-4189-8a89-fcc4ca92d652"], "title": []}]',
'dataset-reference-date': u'[{"type": "publication", "value": "2011-09-08"}]',
'frequency-of-update': u'daily',
'licence': u'["Use of the One Scotland Gazetteer data used by this this service is available to any organisation that is a member of the One Scotland Mapping Agreement. It is not currently commercially available", "http://www.test.gov.uk/licenseurl"]',
'licence_url': u'http://www.test.gov.uk/licenseurl',
'metadata-date': u'2011-09-08T16:07:32',
'metadata-language': u'eng',
'spatial-data-service-type': u'other',
'spatial-reference-system': u'OSGB 1936 / British National Grid (EPSG:27700)',
'temporal_coverage-from': u'["1904-06-16"]',
'temporal_coverage-to': u'["2004-06-16"]',
}
for key,value in expected_extras.iteritems():
extra_value = self.find_extra(package_dict, key)
if extra_value is None:
raise AssertionError('Extra %s not present in package' % key)
if not extra_value == value:
raise AssertionError('Unexpected value for extra %s: %s (was expecting %s)' % \
(key, package_dict['extras'][key], value))
expected_resource = {
'ckan_recommended_wms_preview': 'True',
'description': 'Link to the GetCapabilities request for this service',
'name': 'Web Map Service (WMS)',
'resource_locator_function': 'download',
'resource_locator_protocol': 'OGC:WMS-1.3.0-http-get-capabilities',
'url': u'http://127.0.0.1:8999/wms/capabilities.xml',
'verified': 'True',
}
resource = package_dict['resources'][0]
for key,value in expected_resource.iteritems():
if not resource[key] == value:
raise AssertionError('Unexpected value in resource for %s: %s (was expecting %s)' % \
(key, resource[key], value))
assert datetime.strptime(resource['verified_date'],'%Y-%m-%dT%H:%M:%S.%f').date() == date.today()
assert resource['format'].lower() == 'wms'
def test_harvest_fields_dataset(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/dataset1.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
assert object_ids, len(object_ids) == 1
# No gather errors
assert len(job.gather_errors) == 0
# Fetch stage always returns True for Single Doc harvesters
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
assert obj.guid == u'test-dataset-1'
harvester.import_stage(obj)
# No object errors
assert len(obj.errors) == 0
package_dict = get_action('package_show_rest')(self.context,{'id':obj.package_id})
assert package_dict
expected = {
'name': u'country-parks-scotland',
'title': u'Country Parks (Scotland)',
'tags': [u'Nature conservation'],
'notes': u'Parks are set up by Local Authorities to provide open-air recreation facilities close to towns and cities. [edited]'
}
for key,value in expected.iteritems():
if not package_dict[key] == value:
raise AssertionError('Unexpected value for %s: %s (was expecting %s)' % \
(key, package_dict[key], value))
if config.get('ckan.harvest.auth.profile') == u'publisher':
assert package_dict['groups'] == [self.publisher.id]
expected_extras = {
# Basic
'harvest_object_id': obj.id,
'guid': obj.guid,
'resource-type': u'dataset',
'responsible-party': u'Scottish Natural Heritage (custodian, distributor)',
'access_constraints': u'["Copyright Scottish Natural Heritage"]',
'contact-email': u'*****@*****.**',
'provider':'',
# Spatial
'bbox-east-long': u'0.205857204',
'bbox-north-lat': u'61.06066944',
'bbox-south-lat': u'54.529947158',
'bbox-west-long': u'-8.97114288',
'spatial': u'{"type": "Polygon", "coordinates": [[[0.205857204, 54.529947158], [0.205857204, 61.06066944], [-8.97114288, 61.06066944], [-8.97114288, 54.529947158], [0.205857204, 54.529947158]]]}',
# Other
'coupled-resource': u'[]',
'dataset-reference-date': u'[{"type": "creation", "value": "2004-02"}, {"type": "revision", "value": "2006-07-03"}]',
'frequency-of-update': u'irregular',
'licence': u'["Reference and PSMA Only", "http://www.test.gov.uk/licenseurl"]',
'licence_url': u'http://www.test.gov.uk/licenseurl',
'metadata-date': u'2011-09-23T10:06:08',
'metadata-language': u'eng',
'spatial-reference-system': u'urn:ogc:def:crs:EPSG::27700',
'temporal_coverage-from': u'["1998"]',
'temporal_coverage-to': u'["2010"]',
}
for key,value in expected_extras.iteritems():
if not key in package_dict['extras']:
raise AssertionError('Extra %s not present in package' % key)
if not package_dict['extras'][key] == value:
raise AssertionError('Unexpected value for extra %s: %s (was expecting %s)' % \
(key, package_dict['extras'][key], value))
expected_resource = {
'description': 'Test Resource Description',
'format': u'',
'name': 'Test Resource Name',
'resource_locator_function': 'download',
'resource_locator_protocol': 'test-protocol',
'resource_type': None,
'size': None,
'url': u'https://gateway.snh.gov.uk/pls/apex_ddtdb2/f?p=101',
}
resource = package_dict['resources'][0]
for key,value in expected_resource.iteritems():
if not resource[key] == value:
raise AssertionError('Unexpected value in resource for %s: %s (was expecting %s)' % \
(key, resource[key], value))
def test_harvest_fields_service(self):
# Create source
source_fixture = {
'title': 'Test Source',
'name': 'test-source',
'url': u'http://127.0.0.1:8999/gemini2.1/service1.xml',
'source_type': u'gemini-single'
}
source, job = self._create_source_and_job(source_fixture)
harvester = GeminiDocHarvester()
object_ids = harvester.gather_stage(job)
assert object_ids, len(object_ids) == 1
# No gather errors
assert len(job.gather_errors) == 0
# Fetch stage always returns True for Single Doc harvesters
assert harvester.fetch_stage(object_ids) == True
obj = HarvestObject.get(object_ids[0])
assert obj, obj.content
assert obj.guid == u'test-service-1'
harvester.import_stage(obj)
# No object errors
assert len(obj.errors) == 0
package_dict = get_action('package_show_rest')(self.context,{'id':obj.package_id})
assert package_dict
expected = {
'name': u'one-scotland-address-gazetteer-web-map-service-wms',
'title': u'One Scotland Address Gazetteer Web Map Service (WMS)',
'tags': [u'Addresses', u'Scottish National Gazetteer'],
'notes': u'This service displays its contents at larger scale than 1:10000. [edited]',
}
for key,value in expected.iteritems():
if not package_dict[key] == value:
raise AssertionError('Unexpected value for %s: %s (was expecting %s)' % \
(key, package_dict[key], value))
if config.get('ckan.harvest.auth.profile') == u'publisher':
assert package_dict['groups'] == [self.publisher.id]
expected_extras = {
# Basic
'harvest_object_id': obj.id,
'guid': obj.guid,
'UKLP': u'True',
'resource-type': u'service',
'access_constraints': u'["No restriction on public access"]',
'responsible-party': u'The Improvement Service (owner)',
'provider':u'The Improvement Service',
'contact-email': u'*****@*****.**',
# Spatial
'bbox-east-long': u'0.5242365625',
'bbox-north-lat': u'61.0243',
'bbox-south-lat': u'54.4764484375',
'bbox-west-long': u'-9.099786875',
'spatial': u'{"type": "Polygon", "coordinates": [[[0.5242365625, 54.4764484375], [0.5242365625, 61.0243], [-9.099786875, 61.0243], [-9.099786875, 54.4764484375], [0.5242365625, 54.4764484375]]]}',
# Other
'coupled-resource': u'[{"href": ["http://scotgovsdi.edina.ac.uk/srv/en/csw?service=CSW&request=GetRecordById&version=2.0.2&outputSchema=http://www.isotc211.org/2005/gmd&elementSetName=full&id=250ea276-48e2-4189-8a89-fcc4ca92d652"], "uuid": ["250ea276-48e2-4189-8a89-fcc4ca92d652"], "title": []}]',
'dataset-reference-date': u'[{"type": "publication", "value": "2011-09-08"}]',
'frequency-of-update': u'daily',
'licence': u'["Use of the One Scotland Gazetteer data used by this this service is available to any organisation that is a member of the One Scotland Mapping Agreement. It is not currently commercially available", "http://www.test.gov.uk/licenseurl"]',
'licence_url': u'http://www.test.gov.uk/licenseurl',
'metadata-date': u'2011-09-08T16:07:32',
'metadata-language': u'eng',
'spatial-data-service-type': u'other',
'spatial-reference-system': u'OSGB 1936 / British National Grid (EPSG:27700)',
'temporal_coverage-from': u'["1904-06-16"]',
'temporal_coverage-to': u'["2004-06-16"]',
}
for key,value in expected_extras.iteritems():
if not key in package_dict['extras']:
raise AssertionError('Extra %s not present in package' % key)
if not package_dict['extras'][key] == value:
raise AssertionError('Unexpected value for extra %s: %s (was expecting %s)' % \
(key, package_dict['extras'][key], value))
# Much of this depends on the particular WMS server working...
expected_resource = {
#'ckan_recommended_wms_preview': 'True',
'description': 'Link to the GetCapabilities request for this service',
'format': 'wms', # Newer CKAN versions lower case resource formats
'name': 'Web Map Service (WMS)',
'resource_locator_function': 'download',
'resource_locator_protocol': 'OGC:WMS-1.3.0-http-get-capabilities',
'resource_type': None,
'size': None,
'url': u'http://127.0.0.1:8999/wms/capabilities.xml',
'verified': 'True',
}
resource = package_dict['resources'][0]
for key,value in expected_resource.iteritems():
if not resource[key] == value:
raise AssertionError('Unexpected value in resource for %s: %s (was expecting %s)' % \
(key, resource[key], value))
#assert datetime.strptime(resource['verified_date'],'%Y-%m-%dT%H:%M:%S.%f').date() == date.today()
# See that the coupled resources are created (half of the link)
coupled_resources = self._get_coupled_resources()
assert_equal(coupled_resources,
set([(u'one-scotland-address-gazetteer-web-map-service-wms', '250ea276-48e2-4189-8a89-fcc4ca92d652', None)]))