def arxiv_derive_inspire_categories(obj, eng):
"""Derive ``inspire_categories`` from the arXiv categories.
Uses side effects to populate the ``inspire_categories`` key
in ``obj.data`` by converting its arXiv categories.
Args:
obj (WorkflowObject): a workflow object.
eng (WorkflowEngine): a workflow engine.
Returns:
None
"""
obj.data.setdefault('inspire_categories', [])
for arxiv_category in get_arxiv_categories(obj.data):
term = classify_field(arxiv_category)
if term:
inspire_category = {
'source': 'arxiv',
'term': term,
}
if inspire_category not in obj.data['inspire_categories']:
obj.data['inspire_categories'].append(inspire_category)
def arxiv_derive_inspire_categories(obj, eng):
"""Derive ``inspire_categories`` from the arXiv categories.
Uses side effects to populate the ``inspire_categories`` key
in ``obj.data`` by converting its arXiv categories.
Args:
obj (WorkflowObject): a workflow object.
eng (WorkflowEngine): a workflow engine.
Returns:
None
"""
obj.data.setdefault('inspire_categories', [])
for arxiv_category in get_arxiv_categories(obj.data):
term = classify_field(arxiv_category)
if term:
inspire_category = {
'source': 'arxiv',
'term': term,
}
if inspire_category not in obj.data['inspire_categories']:
obj.data['inspire_categories'].append(inspire_category)
def inspire_categories(self, key, value):
schema = load_schema('elements/inspire_field')
valid_sources = schema['properties']['source']['enum']
inspire_categories = self.get('inspire_categories', [])
scheme = force_single_element(value.get('2'))
if scheme == 'arXiv': # XXX: we skip arXiv categories here because
return inspire_categories # we're going to add them later in a filter.
source = force_single_element(value.get('9', '')).lower()
if source not in valid_sources:
if source == 'automatically added based on dcc, ppf, dk':
source = 'curator'
elif source == 'submitter':
source = 'user'
else:
source = None
terms = force_list(value.get('a'))
for _term in terms:
term = classify_field(_term)
if term:
inspire_categories.append({
'term': term,
'source': source,
})
return inspire_categories
def parse(self):
"""Extract an arXiv record into an Inspire HEP record.
Returns:
dict: the same record in the Inspire Literature schema.
"""
self.builder.add_abstract(abstract=self.abstract, source=self.source)
self.builder.add_title(title=self.title, source=self.source)
for license in self.licenses:
self.builder.add_license(**license)
for author in self.authors:
self.builder.add_author(author)
self.builder.add_number_of_pages(self.number_of_pages)
self.builder.add_publication_info(**self.publication_info)
for collab in self.collaborations:
self.builder.add_collaboration(collab)
for doi in self.dois:
self.builder.add_doi(**doi)
self.builder.add_preprint_date(self.preprint_date)
if self.public_note:
self.builder.add_public_note(self.public_note, self.source)
for rep_number in self.report_numbers:
self.builder.add_report_number(rep_number, self.source)
self.builder.add_arxiv_eprint(self.arxiv_eprint, self.arxiv_categories)
self.builder.add_private_note(self.private_note)
self.builder.add_document_type(self.document_type)
normalized_categories = [
classify_field(arxiv_cat) for arxiv_cat in self.arxiv_categories
]
self.builder.add_inspire_categories(dedupe_list(normalized_categories),
'arxiv')
return self.builder.record
def test_classify_field_ignores_case():
expected = 'Astrophysics'
result = utils.classify_field('ASTRO-PH.CO')
assert expected == result
def test_classify_field_returns_other_if_category_not_found():
expected = 'Other'
result = utils.classify_field('quant-bio')
assert expected == result
def test_classify_field_normalizes_arxiv_category():
expected = 'Math and Math Physics'
result = utils.classify_field('math-dg')
assert expected == result
def test_classify_field_returns_category_for_inspire_category():
expected = 'Astrophysics'
result = utils.classify_field('Astrophysics')
assert expected == result
def test_classify_field_returns_category_for_arxiv_category():
expected = 'Math and Math Physics'
result = utils.classify_field('math.AG')
assert expected == result
def test_classify_field_returns_none_on_non_string_value():
assert utils.classify_field(0) is None
def test_classify_field_returns_none_on_falsy_value():
assert utils.classify_field('') is None
