def setUp(self):
self.NAME = 'ora_solr'
self.END = Ora().ENDPOINT
self.FIELD = 'author'
# We are going to use the following thesis as our test item.
# http://ora.ox.ac.uk/objects/uuid:83530474-369e-417b-a8db-ac06ebf42c84
self.AUTHOR = 'cummings'
self.TITLE = 'neural control of convergence eye movements'
self.EID = '83530474-369e-417b-a8db-ac06ebf42c84'
self.SEARCH = fetch.Search(self.NAME)
self.DATEFIELD = 'timestamp'
self.EDATE = '2013-01-21'
self.ETIME = '11:14:22.227Z'
self.EDATETIME = '%sT%s' % (self.EDATE, self.ETIME)
self.JOINER = '&'
# These expected value might change. Correct as of 18th July 2013
# The total expected is due to ORA defaulting return 10 rows.
self.TOTAL_EXPECTED = 10
self.ROWS_EXPECTED = 2
self.DOCS_EXPECTED = 334
self.TITLE_NOQUOTES_EXPECTED = 112100
self.TOTAL_DATERANGE = 250
# Total until able to explain why it has changed.
self.TOTAL_DATERANGE = 248
def setUp(self):
self.NAME = 'plos_test'
p = Plos()
self.END = p.ENDPOINT
self.KEY = p.KEY
self.URL_API_KEY = p.URL_KEY_FIELD
self.SEARCH = fetch.Search(self.NAME)
def setUp(self):
self.NAME = 'ora_solr_idlist'
self.END = Ora().ENDPOINT
self.FIELD = 'recordContentSource'
self.VALUE = 'polonsky'
# Did a visual check of ORA to confirm this id is from the source above.
self.CHECK_ID = 'uuid:278c6978-9421-46af-af61-a062a2044591'
self.SEARCH = fetch.Search(self.NAME)
self.TOTAL_EXPECTED = 1242
def _fetch_ids(self):
'''Obtain the IDs for the items we want to get totals for.'''
start = time.time()
search = fetch.Search('IDs fetching')
ids, log = search.auto_list_ids(self.ENDPOINT, self.VALUE, self.FIELD)
self.REPORT_METHOD.update(log)
self.RAW_IDS = ids
self.REPORT_METHOD['3a. Seconds taken to find IDs'] = time.time(
) - start
def data_loader(self, year, month, day):
'''Return the total of items with the same year, month and day.'''
self.SEARCH = fetch.Search(self.NAME)
self.SEARCH.set_endpoint(self.END)
# We might as well reduce the amount of data returned
self.SEARCH.set_rows(2) # only two items
self.SEARCH.set_field_getlist(('id',self.FIELD)) # and two fields
# This data loader requires us to restrict the search by date
wanted = self.SEARCH.format_date(year, month, day)
self.SEARCH.query_daterange(self.FIELD, wanted, wanted)
# Now can get the data.
if self.ENABLE_GET_DOCUMENTS:
unused = self.SEARCH.get_documents() # execute the query
return self.SEARCH.DOCS_FOUND
else: # simulate with obviously wrong numbers
return year+month+day+10000
def setUp(self):
self.NAME = 'dfinder_solr'
self.END = Datafinder8000().ENDPOINT
self.FIELD = 'silo'
# We are going to use the following thesis as our test item.
self.SILO = 'eprints'
self.DATEFIELD = 'timestamp'
self.TID = 'oai:generic-eprints-org:774'
self.EDATE = '2012-08-21'
self.ETIME = '15:13:33.521Z'
self.DATEEMBARG = '2082-08-21'
self.SEARCH = fetch.Search(self.NAME)
# These expected results are correct as of 3rd September 2013
self.EXPECTED_TOTAL = 331
self.EXPECTED_DATERANGE_TOTAL = 1814
self.EXPECTED_EMBARG_TOTAL = 175
def setUp(self):
self.NAME = 'plos_solr'
p = Plos()
self.END = p.ENDPOINT
self.KEY = p.KEY
self.URL_API_KEY = p.URL_KEY_FIELD
self.AUTHOR = 'Majlender'
self.AUTHOR2 = 'Welling'
self.AUTHOR_NONASCII = u"Björk"
self.TITLE = 'Open Access to the Scientific Journal Literature'
self.EID = "10.1371/journal.pone.0011273"
self.DATEFIELD = 'publication_date'
self.EDATE = '2010-06-23'
self.ETIME = '00:00:00Z'
self.EDATETIME = '%sT%s' % (self.EDATE, self.ETIME)
self.SEARCH = fetch.Search(self.NAME)
self.JOINER = p.AND_JOINER
# These expected value might change. Correct as
self.DOCS_EXPECTED = 8 #of 26th July 2013
self.DATE_EXPECTED = 259
def setUp(self):
self.NAME = 'ora_solr'
self.END = Ora().ENDPOINT
self.FIELD = 'author'
self.AUTHOR = 'cummings'
self.SEARCH = fetch.Search(self.NAME)