def get_next_pid(self, namespace=None, count=None):
"""
Request next available pid or pids from Fedora, optionally in a specified
namespace. Calls :meth:`ApiFacade.getNextPID`.
.. deprecated :: 0.14
Mint pids for new objects with
:func:`eulcore.fedora.models.DigitalObject.get_default_pid`
instead, or call :meth:`ApiFacade.getNextPID` directly.
:param namespace: (optional) get the next pid in the specified pid namespace;
otherwise, Fedora will return the next pid in the configured default namespace.
:param count: (optional) get the specified number of pids; by default, returns 1 pid
:rtype: string or list of strings
"""
# this method should no longer be needed - default pid logic moved to DigitalObject
warnings.warn(
"""get_next_pid() method is deprecated; you should mint new pids via DigitalObject or ApiFacade.getNextPID() instead.""",
DeprecationWarning,
)
kwargs = {}
if namespace:
kwargs["namespace"] = namespace
if count:
kwargs["numPIDs"] = count
data, url = self.api.getNextPID(**kwargs)
nextpids = parse_xml_object(NewPids, data, url)
if count is None:
return nextpids.pids[0]
else:
return nextpids.pids
def find_objects(self, terms=None, type=None, chunksize=None, **kwargs):
"""
Find objects in Fedora. Find query should be generated via keyword
args, based on the fields in Fedora documentation. By default, the
query uses a contains (~) search for all search terms. Calls
:meth:`ApiFacade.findObjects`. Results seem to return consistently
in ascending PID order.
Example usage - search for all objects where the owner contains 'jdoe'::
repository.find_objects(ownerId='jdoe')
Supports all search operators provided by Fedora findObjects query (exact,
gt, gte, lt, lte, and contains). To specify the type of query for
a particular search term, call find_objects like this::
repository.find_objects(ownerId__exact='lskywalker')
repository.find_objects(date__gt='20010302')
:param type: type of objects to return; defaults to :class:`DigitalObject`
:param chunksize: number of objects to return at a time
:rtype: generator for list of objects
"""
type = type or self.default_object_type
find_opts = {"chunksize": chunksize}
search_operators = {"exact": "=", "gt": ">", "gte": ">=", "lt": "<", "lte": "<=", "contains": "~"}
if terms is not None:
find_opts["terms"] = terms
else:
conditions = []
for field, value in kwargs.iteritems():
if "__" in field:
field, filter = field.split("__")
if filter not in search_operators:
raise Exception("Unsupported search filter '%s'" % filter)
op = search_operators[filter]
else:
op = search_operators["contains"] # default search mode
if field in self.search_fields_aliases:
field = self.search_fields_aliases[field]
if field not in self.search_fields:
raise Exception("Error generating Fedora findObjects query: unknown search field '%s'" % field)
if " " in value:
# if value contains whitespace, it must be delimited with single quotes
value = "'%s'" % value
conditions.append("%s%s%s" % (field, op, value))
query = " ".join(conditions)
find_opts["query"] = query
data, url = self.api.findObjects(**find_opts)
chunk = parse_xml_object(SearchResults, data, url)
while True:
for result in chunk.results:
yield type(self.api, result.pid)
if chunk.session_token:
data, url = self.api.findObjects(session_token=chunk.session_token, **find_opts)
chunk = parse_xml_object(SearchResults, data, url)
else:
break
