def get_statement(self, refresh=False):
if not refresh and self._statement:
return self._statement
if not self.dataverse:
raise NoContainerError('This dataset has not been added to a Dataverse.')
if not self.statement_uri:
# Try to find statement uri without a request to the server
link = get_element(
self.get_entry(),
tag='link',
attribute='rel',
attribute_value='http://purl.org/net/sword/terms/statement',
)
if link is None:
# Find link with request to server
link = get_element(
self.get_entry(refresh=True),
tag='link',
attribute='rel',
attribute_value='http://purl.org/net/sword/terms/statement',
)
self.statement_uri = link.get('href')
resp = requests.get(self.statement_uri, auth=self.connection.auth)
if resp.status_code != 200:
raise ConnectionError('Statement could not be retrieved.')
self._statement = resp.content
return self._statement
def get_statement(self, refresh=False):
if not refresh and self._statement:
return self._statement
if not self.dataverse:
raise NoContainerError(
'This dataset has not been added to a Dataverse.')
if not self.statement_uri:
# Try to find statement uri without a request to the server
link = get_element(
self.get_entry(),
tag='link',
attribute='rel',
attribute_value='http://purl.org/net/sword/terms/statement',
)
if link is None:
# Find link with request to server
link = get_element(
self.get_entry(refresh=True),
tag='link',
attribute='rel',
attribute_value='http://purl.org/net/sword/terms/statement',
)
self.statement_uri = link.get('href')
resp = requests.get(self.statement_uri, auth=self.connection.auth)
if resp.status_code != 200:
raise ConnectionError('Statement could not be retrieved.')
self._statement = resp.content
return self._statement
def test_init_from_xml(self):
dataset = Dataset.from_xml_file(ATOM_DATASET)
title = utils.get_element(dataset.get_entry(),
namespace='dcterms',
tag='title').text
publisher = utils.get_element(dataset.get_entry(),
namespace='dcterms',
tag='rights').text
assert title == 'Roasting at Home'
assert publisher == 'Creative Commons CC-BY 3.0 (unported) http://creativecommons.org/licenses/by/3.0/'
def test_init(self):
dataset = Dataset(title='My Dataset', publisher='Mr. Pub Lisher')
title = utils.get_element(dataset._entry,
namespace='dcterms',
tag='title').text
publisher = utils.get_element(dataset._entry,
namespace='dcterms',
tag='publisher').text
assert title == 'My Dataset'
assert title == dataset.title
assert publisher == 'Mr. Pub Lisher'
def test_get_element(self):
with open(ATOM_DATASET) as f:
entry = f.read()
# One value
title = utils.get_element(entry, 'title', 'dcterms').text
self.assertEqual(title, 'Roasting at Home')
# Two values
creator = utils.get_element(entry, 'creator', 'dcterms').text
self.assertEqual(creator, 'Peets, John')
# No values
nonsense = utils.get_element(entry, 'nonsense', 'booga')
self.assertIsNone(nonsense)
def test_get_element(self):
with open(ATOM_STUDY) as f:
entry = f.read()
# One value
title = utils.get_element(entry, 'title', 'dcterms').text
self.assertEqual(title, 'Roasting at Home')
# Two values
creator = utils.get_element(entry, 'creator', 'dcterms').text
self.assertEqual(creator, 'Peets, John')
# No values
nonsense = utils.get_element(entry, 'nonsense', 'booga')
self.assertIsNone(nonsense)
def test_init_from_xml(self):
dataset = Dataset.from_xml_file(ATOM_DATASET)
title = utils.get_element(
dataset.get_entry(),
namespace='dcterms',
tag='title'
).text
publisher = utils.get_element(
dataset.get_entry(),
namespace='dcterms',
tag='rights'
).text
self.assertEqual(title, 'Roasting at Home')
self.assertEqual(publisher, 'Creative Commons CC-BY 3.0 (unported) http://creativecommons.org/licenses/by/3.0/')
def test_init_from_xml(self):
study = Study.from_xml_file(ATOM_STUDY)
title = utils.get_element(
study.get_entry(),
namespace='dcterms',
tag='title'
).text
publisher = utils.get_element(
study.get_entry(),
namespace='dcterms',
tag='rights'
).text
self.assertEqual(title, 'Roasting at Home')
self.assertEqual(publisher, 'Creative Commons CC-BY 3.0 (unported) http://creativecommons.org/licenses/by/3.0/')
def test_init(self):
study = Study(title='My Study', publisher='Mr. Pub Lisher')
title = utils.get_element(
study._entry,
namespace='dcterms',
tag='title'
).text
publisher = utils.get_element(
study._entry,
namespace='dcterms',
tag='publisher'
).text
self.assertEqual(title, 'My Study')
self.assertEqual(publisher, 'Mr. Pub Lisher')
def test_init(self):
dataset = Dataset(title='My Dataset', publisher='Mr. Pub Lisher')
title = utils.get_element(
dataset._entry,
namespace='dcterms',
tag='title'
).text
publisher = utils.get_element(
dataset._entry,
namespace='dcterms',
tag='publisher'
).text
self.assertEqual(title, 'My Dataset')
self.assertEqual(title, dataset.title)
self.assertEqual(publisher, 'Mr. Pub Lisher')
def test_get_element(self):
with open(ATOM_DATASET) as f:
entry = f.read()
# One value
title = utils.get_element(entry, 'title', 'dcterms').text
assert title == 'Roasting at Home'
# Two values
creator = utils.get_element(entry, 'creator', 'dcterms').text
assert creator == 'Peets, John'
# No values
nonsense = utils.get_element(entry, 'nonsense', 'booga')
assert nonsense is None
def test_get_element(self):
with open(ATOM_DATASET) as f:
entry = f.read()
# One value
title = utils.get_element(entry, 'title', 'dcterms').text
assert title == 'Roasting at Home'
# Two values
creator = utils.get_element(entry, 'creator', 'dcterms').text
assert creator == 'Peets, John'
# No values
nonsense = utils.get_element(entry, 'nonsense', 'booga')
assert nonsense is None
def test_init(self):
dataset = Dataset(title='My Dataset', publisher='Mr. Pub Lisher')
title = utils.get_element(
dataset._entry,
namespace='dcterms',
tag='title'
).text
publisher = utils.get_element(
dataset._entry,
namespace='dcterms',
tag='publisher'
).text
assert title == 'My Dataset'
assert title == dataset.title
assert publisher == 'Mr. Pub Lisher'
def __init__(self, entry=SWORD_BOOTSTRAP, dataverse=None, edit_uri=None,
edit_media_uri=None, statement_uri=None, **kwargs):
"""
Datasets must have a title, description, and author.
This can be specified in the atom entry or as kwargs
"""
self.dataverse = dataverse
self.edit_uri = edit_uri
self.edit_media_uri = edit_media_uri
self.statement_uri = statement_uri
self.is_deleted = False
self._entry = etree.XML(entry) if isinstance(entry, str) else entry
self._statement = None
self._metadata = {}
self._id = None
# Updates sword entry from keyword arguments
for key in kwargs:
value = kwargs[key]
if isinstance(value, list):
for item in value:
add_field(self._entry, key, item, 'dcterms')
else:
add_field(self._entry, key, value, 'dcterms')
self.title = get_element(
self._entry, tag='title', namespace='dcterms'
).text
def __init__(self,
entry=SWORD_BOOTSTRAP,
dataverse=None,
edit_uri=None,
edit_media_uri=None,
statement_uri=None,
**kwargs):
"""
Datasets must have a title, description, and author.
This can be specified in the atom entry or as kwargs
"""
self.dataverse = dataverse
self.edit_uri = edit_uri
self.edit_media_uri = edit_media_uri
self.statement_uri = statement_uri
self.is_deleted = False
self._entry = etree.XML(entry) if isinstance(entry, str) else entry
self._statement = None
self._metadata = {}
self._id = None
# Updates sword entry from keyword arguments
for key in kwargs:
value = kwargs[key]
if isinstance(value, list):
for item in value:
add_field(self._entry, key, item, 'dcterms')
else:
add_field(self._entry, key, value, 'dcterms')
self.title = get_element(self._entry, tag='title',
namespace='dcterms').text
def title(self):
return sanitize(
get_element(
self.collection,
namespace='atom',
tag='title',
).text)
def get_state(self, refresh=False):
if self.is_deleted:
return 'DEACCESSIONED'
return get_element(self.get_statement(refresh),
tag='category',
attribute='term',
attribute_value='latestVersionState').text
def get_state(self, refresh=False):
if self.is_deleted:
return 'DEACCESSIONED'
return get_element(
self.get_statement(refresh),
tag='category',
attribute='term',
attribute_value='latestVersionState'
).text
def from_dataverse(cls, entry_element, dataverse):
# Entry not in appropriate format--extract relevant metadata
id_element = get_element(entry_element, tag='id')
title_element = get_element(entry_element, tag='title')
edit_media_element = get_element(
entry_element,
tag='link',
attribute='rel',
attribute_value='edit-media',
)
return cls(
title=title_element.text,
id=id_element.text,
dataverse=dataverse,
edit_uri=entry_element.base,
edit_media_uri=edit_media_element.get('href'),
)
def from_dataverse(cls, entry_element, dataverse):
# Entry not in appropriate format--extract relevant metadata
id_element = get_element(entry_element, tag='id')
title_element = get_element(entry_element, tag='title')
edit_media_element = get_element(
entry_element,
tag='link',
attribute='rel',
attribute_value='edit-media',
)
return cls(
title=title_element.text,
id=id_element.text,
dataverse=dataverse,
edit_uri=entry_element.base,
edit_media_uri=edit_media_element.get('href'),
)
def _refresh(self, receipt=None):
if receipt:
self.edit_uri = get_element(receipt,
tag='link',
attribute='rel',
attribute_value='edit').get('href')
self.edit_media_uri = get_element(
receipt,
tag='link',
attribute='rel',
attribute_value='edit-media').get('href')
self.statement_uri = get_element(
receipt,
tag='link',
attribute='rel',
attribute_value='http://purl.org/net/sword/terms/statement'
).get('href')
self.get_statement(refresh=True)
self.get_entry(refresh=True)
self.get_metadata('latest', refresh=True)
def _refresh(self, receipt=None):
if receipt:
self.edit_uri = get_element(
receipt,
tag='link',
attribute='rel',
attribute_value='edit'
).get('href')
self.edit_media_uri = get_element(
receipt,
tag='link',
attribute='rel',
attribute_value='edit-media'
).get('href')
self.statement_uri = get_element(
receipt,
tag='link',
attribute='rel',
attribute_value='http://purl.org/net/sword/terms/statement'
).get('href')
self.get_statement(refresh=True)
self.get_entry(refresh=True)
self.get_metadata('latest', refresh=True)
def is_published(self):
# Always check latest version
collection_info = requests.get(
self.collection.get('href'),
auth=self.connection.auth,
).content
status_tag = get_element(
collection_info,
namespace='http://purl.org/net/sword/terms/state',
tag='dataverseHasBeenReleased',
)
status = status_tag.text
return status.lower() == 'true'
def is_published(self):
# Always check latest version
collection_info = requests.get(
self.collection.get('href'),
auth=self.connection.auth,verify=self.connection.verify
).content
status_tag = get_element(
collection_info,
namespace='http://purl.org/net/sword/terms/state',
tag='dataverseHasBeenReleased',
)
status = status_tag.text
return status.lower() == 'true'
def title(self):
return sanitize(get_element(
self.collection,
namespace='atom',
tag='title',
).text)
def citation(self):
return get_element(
self.get_entry(),
namespace='http://purl.org/dc/terms/',
tag='bibliographicCitation'
).text
def citation(self):
return get_element(self.get_entry(),
namespace='http://purl.org/dc/terms/',
tag='bibliographicCitation').text