def check_records(records):
for record in records:
if is_springer(record):
rec_doc = BibRecDocs(int(record.record_id))
rec_docs = rec_doc.list_latest_files()
for doc in rec_docs:
if doc.get_format() == '.xml':
f = open(doc.get_full_path())
content = f.read()
try:
del record['100']
del record['700']
record.amended = True
except:
pass
first_author = True
try:
if "-//NLM//DTD JATS" in content:
jats = JATSParser()
authors = jats.get_authors(parseString(content))
else:
app = NLMParser()
authors = app.get_authors(parseString(content))
except:
record.warn('Problem with parsing XML.')
continue
for author in authors:
if author.get('surname'):
subfields = [
('a',
'%s, %s' % (author.get('surname'),
author.get('given_name')
or author.get('initials', '')))
]
else:
subfields = [('a', '%s' % (author.get('name', '')))
]
if 'orcid' in author:
subfields.append(('j', author['orcid']))
if 'affiliation' in author:
for aff in author["affiliation"]:
subfields.append(('v', aff))
add_nations_field(subfields)
if author.get('email'):
subfields.append(('m', author['email']))
if first_author:
record.add_field('100__',
value='',
subfields=subfields)
first_author = False
else:
record.add_field('700__',
value='',
subfields=subfields)
def check_records(records):
for record in records:
if is_springer(record):
rec_doc = BibRecDocs(int(record.record_id))
rec_docs = rec_doc.list_latest_files()
for doc in rec_docs:
if doc.get_format() == '.xml':
f = open(doc.get_full_path())
content = f.read()
try:
del record['100']
del record['700']
record.amended = True
except:
pass
first_author = True
try:
if "-//NLM//DTD JATS" in content:
jats = JATSParser()
authors = jats.get_authors(parseString(content))
else:
app = NLMParser()
authors = app.get_authors(parseString(content))
except:
record.warn('Problem with parsing XML.')
continue
for author in authors:
if author.get('surname'):
subfields = [('a', '%s, %s' % (author.get('surname'), author.get('given_name') or author.get('initials', '')))]
else:
subfields = [('a', '%s' % (author.get('name', '')))]
if 'orcid' in author:
subfields.append(('j', author['orcid']))
if 'affiliation' in author:
for aff in author["affiliation"]:
subfields.append(('v', aff))
add_nations_field(subfields)
if author.get('email'):
subfields.append(('m', author['email']))
if first_author:
record.add_field('100__', value='', subfields=subfields)
first_author = False
else:
record.add_field('700__', value='', subfields=subfields)
class JATSUtilsTests(unittest.TestCase):
def setUp(self):
self.jats_parser = JATSParser()
def test_get_orcid(self):
"""
See http://jats.nlm.nih.gov/archiving/tag-library/1.1d1/n-dsw0.html for orcid in contrib tag
"""
xml = parseString(
"""<contrib>
<contrib-id contrib-id-type="orcid">http://orcid.org/1792-3336-9172-961X</contrib-id>
<name><surname>Fauller</surname>
<given-names>Betty Lou</given-names>
</name>
<degrees>BA, MA</degrees>
</contrib>""")
self.assertEqual(self.jats_parser._get_orcid(xml), '1792-3336-9172-961X')
def setUp(self):
self.jats_parser = JATSParser()