class ExtraSchema(Schema):
key = Str()
value = Str()
class XMLDatasetSchema(Schema):
ext_ident = Str(data_key='extIdent',
validate=validate.Length(max=36),
required=True)
int_ident = Int(data_key='intIdent')
status = Str(data_key='@status',
validate=validate.OneOf(choices=['draft', 'published']))
title_pl = Str()
title_en = Str()
notes_pl = Str()
notes_en = Str()
url = URL(allow_none=True)
update_frequency = Str(data_key='updateFrequency')
license = Str()
license_chosen = Int(allow_none=True)
license_condition_db_or_copyrighted = Str(allow_none=True)
license_condition_modification = Bool(allow_none=True)
license_condition_personal_data = Str(allow_none=True)
license_condition_responsibilities = Str(allow_none=True)
license_condition_source = Bool(allow_none=True)
created = DateTime(data_key='created', allow_none=True)
modified = DateTime(data_key='lastUpdateDate', allow_none=True)
categories = List(Str())
resources = Nested(XMLResourceSchema, many=True)
tags = Nested(XMLTagSchema, many=True)
class Meta:
ordered = True
unknown = EXCLUDE
@pre_load
def prepare_data(self, data, **kwargs):
if 'title' in data and isinstance(data.get('title'), dict):
data['title_en'] = data['title'].get('english', '')
data['title_pl'] = data['title'].get('polish', '')
if 'conditions' in data:
data['license_condition_source'] = data['conditions'].get(
'source', False)
data['license_condition_modification'] = data['conditions'].get(
'modification', False)
data['license_condition_responsibilities'] = data[
'conditions'].get('responsibilities')
data['license_condition_db_or_copyrighted'] = data[
'conditions'].get('dbOrCopyrighted')
license_text_to_num = dict(
(row[1], row[0]) for row in Dataset.LICENSES)
license_chosen_text = data['conditions'].get(
'dbOrCopyrightedLicenseChosen')
data['license_chosen'] = license_text_to_num.get(
license_chosen_text)
data['license_condition_personal_data'] = data['conditions'].get(
'personalData')
if 'description' in data and isinstance(data.get('description'), dict):
data['notes_en'] = data['description'].get('english', '')
data['notes_pl'] = data['description'].get('polish', '')
if 'tags' in data:
data['tags'] = data['tags'].get('tag', [])
if 'categories' in data:
if 'category' in data['categories']: # XSD SCHEMA >= 1.1
data['categories'] = data['categories']['category']
else:
data['categories'] = [str(row) for row in data['categories']]
if 'resources' in data:
data['resources'] = data['resources'].get('resource', [])
int_ident = data.get('intIdent')
if int_ident:
self.context['dataset_int_ident'] = int_ident
return data
@validates_schema
def validate_int_ident(self, data, **kwargs):
int_ident = data.get('int_ident')
organization = self.context['organization']
if int_ident and organization and not Dataset.raw.filter(
id=int_ident, organization=organization).exists():
msg = _(
'Dataset with id: %(d_id)s and institution: "%(ins)s" was not found.'
) % {
'd_id': int_ident,
'ins': organization.title
}
raise ValidationError(msg, field_name='int_ident')
@validates_schema
def validate_license_condition_personal_data(self, data, **kwargs):
field_name = 'license_condition_personal_data'
if data.get(field_name):
raise ValidationError(
message=
_('Chosen conditions for re-use mean that they contain personal data. '
'Please contact the administrator at [email protected].'),
field_name=field_name,
)
@validates_schema
def validate_license_condition_db_or_copyrighted(self, data, **kwargs):
field_name = 'license_condition_db_or_copyrighted'
if data.get(field_name) and not data.get('license_chosen'):
raise ValidationError(
message=
_("Field 'dbOrCopyrightedLicenseChosen' is required if field 'dbOrCopyrighted' is provided."
),
field_name=field_name,
)
@validates_schema
def validate_license_chosen(self, data, **kwargs):
field_name = 'license_chosen'
if data.get(field_name
) and not data.get('license_condition_db_or_copyrighted'):
raise ValidationError(
message=
_("Field 'dbOrCopyrighted' is required if field 'dbOrCopyrightedLicenseChosen' is provided."
),
field_name=field_name,
)
class DatasetSchema(Schema):
author = Str()
author_email = Str()
creator_user_id = UUID()
extras = Nested(ExtraSchema, many=True)
groups = Nested(CategorySchema, many=True)
license_id = Str()
license_title = Str()
license_url = URL()
maintainer = Str()
maintainer_email = Str()
created = DateTime(data_key='metadata_created')
modified = DateTime(data_key='metadata_modified', allow_none=True)
slug = Str(data_key='name')
notes = Str()
num_resources = Int()
num_tags = Int()
ext_ident = Str(data_key='id', validate=validate.Length(max=36))
isopen = Bool()
organization = Nested(OrganizationSchema, many=False)
owner_org = UUID()
private = Bool()
relationships_as_object = Nested(RelationshipObjectSchema, many=True)
relationships_as_subject = Nested(RelationshipSubjectSchema, many=True)
resources = Nested(ResourceSchema, many=True)
revision_id = UUID()
status = Str(data_key='state')
tags = Nested(TagSchema, many=True)
title = Str()
type = Str()
url = Str()
version = Str()
class Meta:
exclude = [
'author', 'author_email', 'creator_user_id', 'extras', 'groups',
'license_title', 'license_url', 'maintainer', 'maintainer_email',
'num_resources', 'num_tags', 'isopen', 'owner_org', 'private',
'relationships_as_object', 'relationships_as_subject',
'revision_id', 'type', 'status', 'url', 'version'
]
ordered = True
unknown = EXCLUDE
class FrozenListSchema(Schema):
items = fields.FrozenList(Str(), allow_none=True)
class SetSchema(Schema):
items = fields.Set(Str(), allow_none=True)
class SampleSchema(Schema):
name = Str(required=True)
salary = Int(required=True)