def test_search_journal_title_no_match(self, mock_urlopen):
mock_urlopen.return_value.read.return_value = \
self.fixture_text('example-08.xml')
journals = romeo.search_journal_title('recycling journal')
# query
mock_urlopen.assert_called_once()
args, kwargs = mock_urlopen.call_args
self.assertEqual(kwargs, {})
self.assertEqual(len(args), 1)
query_args = parse_qs(urlsplit(args[0]).query)
self.assertEqual(query_args['jtitle'], ['recycling journal'])
# response
self.assertEqual(len(journals), 0)
def test_search_journal_title_no_match(self, mock_urlopen):
mock_urlopen.return_value.read.return_value = \
self.fixture_text('example-08.xml')
journals = romeo.search_journal_title('recycling journal')
# query
mock_urlopen.assert_called_once()
args, kwargs = mock_urlopen.call_args
self.assertEqual(kwargs, {})
self.assertEqual(len(args), 1)
query_args = parse_qs(urlsplit(args[0]).query)
self.assertEqual(query_args['jtitle'], ['recycling journal'])
# response
self.assertEqual(len(journals), 0)
def test_search_journal_title_single_example(self, mock_urlopen):
mock_urlopen.return_value.read.return_value = \
self.fixture_text('example-05.xml')
journals = romeo.search_journal_title('revista argentina de cardiologia')
publisher = journals[0].publisher_details()
# query
mock_urlopen.assert_called_once()
args, kwargs = mock_urlopen.call_args
self.assertEqual(kwargs, {})
self.assertEqual(len(args), 1)
query_args = parse_qs(urlsplit(args[0]).query)
self.assertEqual(query_args['jtitle'], ['revista argentina de cardiologia'])
# response
self.assertEqual(len(journals), 1)
self.assertEqual(journals[0].title, 'Revista Argentina de Cardiologia')
self.assertEqual(journals[0].issn, '0034-7000')
self.assertTrue(isinstance(publisher, romeo.Publisher))
self.assertEqual(publisher.name, u'Sociedad Argentina de Cardiolog\xeda')
def test_search_journal_title_multiple_example(self, mock_urlopen):
mock_urlopen.return_value.read.return_value = \
self.fixture_text('example-04.xml')
journals = romeo.search_journal_title('dna')
# query
mock_urlopen.assert_called_once()
args, kwargs = mock_urlopen.call_args
self.assertEqual(kwargs, {})
self.assertEqual(len(args), 1)
query_args = parse_qs(urlsplit(args[0]).query)
self.assertEqual(query_args['jtitle'], ['dna'])
# response
self.assertEqual(len(journals), 5)
self.assertEqual(journals[0].title, 'DNA')
self.assertEqual(journals[0].issn, '0198-0238')
self.assertEqual(journals[1].title, 'DNA and Cell Biology')
self.assertEqual(journals[1].issn, '1044-5498')
self.assertEqual(journals[1].publisher_zetoc, 'Mary Ann Liebert, Inc.')
self.assertEqual(journals[1].publisher_romeo, 'Mary Ann Liebert')
def test_search_journal_title_multiple_example(self, mock_urlopen):
mock_urlopen.return_value.read.return_value = \
self.fixture_text('example-04.xml')
journals = romeo.search_journal_title('dna')
# query
mock_urlopen.assert_called_once()
args, kwargs = mock_urlopen.call_args
self.assertEqual(kwargs, {})
self.assertEqual(len(args), 1)
query_args = parse_qs(urlsplit(args[0]).query)
self.assertEqual(query_args['jtitle'], ['dna'])
# response
self.assertEqual(len(journals), 5)
self.assertEqual(journals[0].title, 'DNA')
self.assertEqual(journals[0].issn, '0198-0238')
self.assertEqual(journals[1].title, 'DNA and Cell Biology')
self.assertEqual(journals[1].issn, '1044-5498')
self.assertEqual(journals[1].publisher_zetoc, 'Mary Ann Liebert, Inc.')
self.assertEqual(journals[1].publisher_romeo, 'Mary Ann Liebert')
def test_search_journal_title_single_example(self, mock_urlopen):
mock_urlopen.return_value.read.return_value = \
self.fixture_text('example-05.xml')
journals = romeo.search_journal_title(
'revista argentina de cardiologia')
publisher = journals[0].publisher_details()
# query
mock_urlopen.assert_called_once()
args, kwargs = mock_urlopen.call_args
self.assertEqual(kwargs, {})
self.assertEqual(len(args), 1)
query_args = parse_qs(urlsplit(args[0]).query)
self.assertEqual(query_args['jtitle'],
['revista argentina de cardiologia'])
# response
self.assertEqual(len(journals), 1)
self.assertEqual(journals[0].title, 'Revista Argentina de Cardiologia')
self.assertEqual(journals[0].issn, '0034-7000')
self.assertTrue(isinstance(publisher, romeo.Publisher))
self.assertEqual(publisher.name,
u'Sociedad Argentina de Cardiolog\xeda')
def handle(self, *args, **options):
self.verbosity = int(options['verbosity']) # 1 = normal, 0 = minimal, 2 = all
self.v_normal = 1
# connection to repository
self.repo = ManagementRepository()
pid_set = self.repo.get_objects_with_cmodel(Publication.ARTICLE_CONTENT_MODEL, type=Publication)
try:
articles = Paginator(pid_set, 100)
except Exception as e:
self.output(0, "Error paginating items: : %s " % (e.message))
#process all Articles
for p in articles.page_range:
try:
objs = articles.page(p).object_list
except Exception as e:
#print error and go to next iteration of loop
self.output(0,"Error getting page: %s : %s " % (p, e.message))
continue
for article in objs:
try:
if not article.exists:
self.output(0, "Skipping %s because pid does not exist" % article.pid)
continue
else:
mods = article.descMetadata.content
if mods.journal is not None:
if mods.journal.title is not None:
try:
journals = romeo.search_journal_title(mods.journal.title, type='starts') if mods.journal.title else []
suggestions = [journal_suggestion_data(journal) for journal in journals]
if mods.journal.title.lower() in map(str.lower, JOURNAL_LIST):
mods.journal.title = suggestions[0]['value']
print "JOURNAL"
print mods.journal.title
article.save()
else:
continue
except:
suggestions = []
# if mods.journal.publisher is not None:
# try:
# publishers = romeo.search_publisher_name(mods.journal.publisher, versions='all')
# suggestions = [publisher_suggestion_data(pub) for pub in publishers]
# mods.journal.publisher = suggestions[0]['value']
# print "PUBLISHER"
# print mods.journal.publisher
# except:
# suggestions = []
else:
continue
except Exception as e:
self.output(0, "Error processing pid: %s : %s " % (article.pid, e.message))
