def _normalize(a_value):
for category in valid_arxiv_categories():
if a_value.lower() == category.lower():
return normalize_arxiv_category(category)
schema = load_schema('elements/inspire_field')
valid_inspire_categories = schema['properties']['term']['enum']
for category in valid_inspire_categories:
if a_value.lower() == category.lower():
return category
field_codes_to_inspire_categories = {
'a': 'Astrophysics',
'b': 'Accelerators',
'c': 'Computing',
'e': 'Experiment-HEP',
'g': 'Gravitation and Cosmology',
'i': 'Instrumentation',
'l': 'Lattice',
'm': 'Math and Math Physics',
'n': 'Theory-Nucl',
'o': 'Other',
'p': 'Phenomenology-HEP',
'q': 'General Physics',
't': 'Theory-HEP',
'x': 'Experiment-Nucl',
}
return field_codes_to_inspire_categories.get(a_value.lower())
def arxiv_categories(self):
categories = self.root.xpath('.//categories/text()').extract_first(
default='[]')
categories = categories.split()
categories_without_old = [
normalize_arxiv_category(arxiv_cat) for arxiv_cat in categories
]
return dedupe_list(categories_without_old)
def arxiv_categories(self, key, value):
category = value.get('a', '')
if category.lower() == 'physics-other':
return None
elif category.lower() == 'physics.acc-phys':
return 'physics.acc-ph'
return normalize_arxiv_category(value.get('a'))
def add_arxiv_categories(record, blob):
if not record.get('arxiv_eprints') or not blob.get('65017'):
return record
for category in force_list(get_value(blob, '65017')):
if category.get('2') == 'arXiv' and category.get('a'):
record['arxiv_eprints'][0]['categories'].append(
normalize_arxiv_category(category['a']))
return record
def arxiv_eprints(self, key, value):
"""Populate the ``arxiv_eprints`` key.
Also populates the ``report_numbers`` key through side effects.
"""
def _get_clean_arxiv_eprint(id_):
return id_.split(':')[-1]
def _is_arxiv_eprint(id_, source):
return source.lower() == 'arxiv'
def _is_hidden_report_number(other_id, source):
return other_id
def _get_clean_source(source):
if source == 'arXiv:reportnumber':
return 'arXiv'
return source
arxiv_eprints = self.get('arxiv_eprints', [])
report_numbers = self.get('report_numbers', [])
values = force_list(value)
for value in values:
id_ = force_single_element(value.get('a', ''))
other_id = force_single_element(value.get('z', ''))
categories = [
normalize_arxiv_category(category)
for category in force_list(value.get('c'))
]
source = force_single_element(value.get('9', ''))
if _is_arxiv_eprint(id_, source):
arxiv_eprints.append({
'categories': categories,
'value': _get_clean_arxiv_eprint(id_),
})
elif _is_hidden_report_number(other_id, source):
report_numbers.append({
'hidden': True,
'source': _get_clean_source(source),
'value': other_id,
})
else:
report_numbers.append({
'source': _get_clean_source(source),
'value': id_,
})
self['report_numbers'] = report_numbers
return arxiv_eprints
def test_normalize_arxiv_category_returns_existing_category_for_wrong_caps():
expected = 'hep-th'
result = utils.normalize_arxiv_category('HeP-Th')
assert expected == result
def test_normalize_arxiv_category_returns_existing_category_for_obsolete():
expected = 'math.FA'
result = utils.normalize_arxiv_category('funct-an')
assert expected == result
def test_normalize_arxiv_category_returns_input_for_inexistent_category():
expected = u'😃'
result = utils.normalize_arxiv_category(u'😃')
assert expected == result
def test_normalize_arxiv_category_returns_input_for_correct_category():
expected = 'hep-th'
result = utils.normalize_arxiv_category('hep-th')
assert expected == result
def test_normalize_arxiv_category_returns_existing_category_when_dot_is_dash():
expected = 'math.FA'
result = utils.normalize_arxiv_category('math-fa')
assert expected == result
