def test_that_db_changes_are_mirrored_in_es(app):
search = LiteratureSearch()
json = {
'$schema': 'http://localhost:5000/schemas/records/hep.json',
'document_type': [
'article',
],
'titles': [
{'title': 'foo'},
],
}
# When a record is created in the DB, it is also created in ES.
record = InspireRecord.create(json)
es_record = search.get_source(record.id)
assert get_title(es_record) == 'foo'
# When a record is updated in the DB, is is also updated in ES.
record['titles'][0]['title'] = 'bar'
record.commit()
es_record = search.get_source(record.id)
assert get_title(es_record) == 'bar'
# When a record is deleted in the DB, it is also deleted in ES.
record._delete(force=True)
with pytest.raises(NotFoundError):
es_record = search.get_source(record.id)
def test_get_title(double_title, single_title, empty_title):
"""Test get title utility."""
assert get_title(double_title) == "Parton distributions with LHC data"
assert get_title(single_title) == "The Large Hadron Collider"
assert get_title(empty_title) == ""
no_title_key = {
"not_titles": []
}
assert get_title(no_title_key) == ""
def test_get_title_returns_empty_string_when_no_titles():
no_titles = Record({})
expected = ''
result = get_title(no_titles)
assert expected == result
def test_get_title_returns_empty_string_when_no_titles():
record = {}
expected = ''
result = get_title(record)
assert expected == result
def test_get_title_returns_empty_string_when_titles_is_empty():
record = {'titles': []}
expected = ''
result = get_title(record)
assert expected == result
def title_rule(self, key, value):
title = get_title({"titles": value})
if title == '':
raise KeyError
subtitle = get_subtitle({"titles": value})
return {"title": title,
"subtitle": subtitle}
def test_get_title_returns_empty_string_when_titles_is_empty():
empty_titles = Record({'titles': []})
expected = ''
result = get_title(empty_titles)
assert expected == result
def build_citesummary(search):
citesummary = []
for i, el in enumerate(search.scan()):
result = el.to_dict()
citesummary.append({
'citations': [],
'collaboration': is_collaboration(result),
'core': is_core(result),
'date': get_date(result),
'document_type': get_document_type(result),
'id': get_id(result),
'subject': get_subject(result),
'title': get_title(result),
})
search_by_literature = LiteratureSearch().query(
'match', references__recid=get_id(result)
).params(
_source=[
'authors.recid',
'collaborations.value',
'control_number',
'earliest_date',
'facet_inspire_doc_type',
'inspire_categories',
'titles.title',
]
)
for el in search_by_literature.scan():
literature_result = el.to_dict()
citesummary[i]['citations'].append({
'collaboration': is_collaboration(literature_result),
'core': is_core(literature_result),
'date': get_date(literature_result),
'document_type': get_document_type(literature_result),
'id': get_id(literature_result),
'selfcite': is_selfcite(
result, literature_result),
'subject': get_subject(literature_result),
'title': get_title(literature_result),
})
return citesummary
def reply_ticket_context(user, obj):
"""Context for literature replies."""
return dict(
object=obj,
user=user,
title=get_title(obj.data),
reason=obj.extra_data.get("reason", ""),
record_url=obj.extra_data.get("url", ""),
)
def conference_information(self):
"""Conference information.
Returns a list with information about conferences related to the
record.
"""
conf_info = []
for pub_info in self['publication_info']:
conference_recid = None
parent_recid = None
parent_rec = {}
conference_rec = {}
if 'conference_record' in pub_info:
conference_rec = replace_refs(pub_info['conference_record'],
'es')
if conference_rec and conference_rec.get('control_number'):
conference_recid = conference_rec['control_number']
else:
conference_rec = {}
if 'parent_record' in pub_info:
parent_rec = replace_refs(pub_info['parent_record'], 'es')
if parent_rec and parent_rec.get('control_number'):
parent_recid = parent_rec['control_number']
else:
parent_rec = {}
conf_info.append(
{
"conference_recid": conference_recid,
"conference_title": get_title(conference_rec),
"parent_recid": parent_recid,
"parent_title":
get_title(parent_rec).replace(
"Proceedings, ", "", 1
),
"page_start": pub_info.get('page_start'),
"page_end": pub_info.get('page_end'),
"artid": pub_info.get('artid'),
}
)
return conf_info
def test_get_title_returns_first_title():
record = {
'titles': [
{'title': 'first title'},
{'title': 'second title'},
],
}
expected = 'first title'
result = get_title(record)
assert expected == result
def test_get_title():
"""Test get title utility."""
double_title = {
"titles": [
{
"source": "arXiv",
"title": "Parton distributions with LHC data"
},
{
"title": "Parton distributions with LHC data"
}
]
}
assert get_title(double_title) == "Parton distributions with LHC data"
single_title = {
"titles": [
{
"subtitle": "Harvest of Run 1",
"title": "The Large Hadron Collider"
}
]
}
assert get_title(single_title) == "The Large Hadron Collider"
empty_title = {
"titles": []
}
assert get_title(empty_title) == ""
no_title_key = {
"not_titles": []
}
assert get_title(no_title_key) == ""
def test_get_title_returns_the_only_title():
single_title = Record({
'titles': [
{
'source': "arXiv",
'title': 'The Large Hadron Collider'
}
]
})
expected = 'The Large Hadron Collider'
result = get_title(single_title)
assert expected == result
def new_ticket_context(user, obj):
"""Context for literature new tickets."""
title = get_title(obj.data)
subject = u"Your suggestion to INSPIRE: {0}".format(title)
user_comment = obj.extra_data.get('formdata', {}).get('extra_comments', '')
identifiers = get_value(obj.data, "external_system_numbers.value") or []
return dict(
email=user.email,
title=title,
identifier=identifiers or "",
user_comment=user_comment,
references=obj.extra_data.get('formdata', {}).get('references'),
object=obj,
subject=subject
)
def test_get_title_returns_first_title():
record = {
'titles': [
{
'title': 'first title'
},
{
'title': 'second title'
},
],
}
expected = 'first title'
result = get_title(record)
assert expected == result
def test_get_title_returns_the_non_arxiv_title():
double_title = Record({
"titles": [
{
"title": "Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia"
},
{
"source": "arXiv",
"title": "Monte Carlo tuning in the presence of Matching"
}
],
})
expected = 'Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia'
result = get_title(double_title)
assert expected == result
def test_get_title_returns_the_non_arxiv_title_with_source():
double_title = InspireRecord({
"titles": [{
"source":
"other",
"title":
"Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia"
}, {
"source": "arXiv",
"title": "Monte Carlo tuning in the presence of Matching"
}],
})
expected = 'Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia'
result = get_title(double_title)
assert expected == result
def test_get_title():
schema = load_schema('hep')
subschema = schema['properties']['titles']
record = {
'titles': [
{
'subtitle': 'A mathematical exposition',
'title': 'The General Theory of Relativity',
},
],
}
assert validate(record['titles'], subschema) is None
expected = 'The General Theory of Relativity'
result = get_title(record)
assert expected == result
def get_institution_papers_datatables_rows(hits):
"""Row used by datatables to render institution papers."""
result = []
title_html = "<a href='/literature/{id}'>{name}</a>"
for hit in hits:
row = []
row.append(
title_html.format(
id=hit.control_number,
name=get_title(hit.to_dict()).encode('utf8')
)
)
ctx = {
'record': hit.to_dict(),
'is_brief': 'true',
'number_of_displayed_authors': 1,
'show_affiliations': 'false',
'collaboration_only': 'true'
}
row.append(render_macro_from_template(
name="render_record_authors",
template="inspirehep_theme/format/record/Inspire_Default_HTML_general_macros.tpl",
ctx=ctx
)
)
try:
row.append(hit.publication_info[0].journal_title)
except AttributeError:
row.append('')
try:
row.append(hit.citation_count)
except AttributeError:
row.append(0)
row.append(hit.earliest_date.split('-')[0])
result.append(row)
return result
def get_institution_papers_datatables_rows(hits):
"""Row used by datatables to render institution papers."""
result = []
title_html = "<a href='/literature/{id}'>{name}</a>"
for hit in hits:
row = []
row.append(
title_html.format(
id=hit.control_number,
name=get_title(hit.to_dict())
)
)
ctx = {
'record': hit.to_dict(),
'is_brief': 'true',
'number_of_displayed_authors': 1,
'show_affiliations': 'false',
'collaboration_only': 'true'
}
row.append(render_macro_from_template(
name="render_record_authors",
template="inspirehep_theme/format/record/Inspire_Default_HTML_general_macros.tpl",
ctx=ctx
)
)
try:
row.append(hit.publication_info[0].journal_title)
except AttributeError:
row.append('')
try:
row.append(hit.citation_count)
except AttributeError:
row.append(0)
row.append(hit.earliest_date.split('-')[0])
result.append(row)
return result
def render_contributions(hits):
"""Render a list of conferences to HTML."""
result = []
title_html = u"<a href='/literature/{id}'>{name}</a>"
for hit in hits:
row = []
row.append(
title_html.format(
id=hit.control_number,
name=get_title(hit.to_dict())
)
)
ctx = {
'record': hit.to_dict(),
'is_brief': 'true',
'number_of_displayed_authors': 1,
'show_affiliations': 'false',
'collaboration_only': 'true'
}
row.append(render_macro_from_template(
name="render_record_authors",
template="inspirehep_theme/format/record/Inspire_Default_HTML_general_macros.tpl",
ctx=ctx
)
)
try:
row.append(hit.publication_info[0].journal_title)
except AttributeError:
row.append('')
try:
row.append(hit.citation_count)
except AttributeError:
row.append(0)
result.append(row)
return result, hits.total
def render_contributions(hits):
"""Render a list of conferences to HTML."""
result = []
title_html = "<a href='/literature/{id}'>{name}</a>"
for hit in hits:
row = []
row.append(
title_html.format(
id=hit.control_number,
name=get_title(hit.to_dict()).encode('utf8')
)
)
ctx = {
'record': hit.to_dict(),
'is_brief': 'true',
'number_of_displayed_authors': 1,
'show_affiliations': 'false',
'collaboration_only': 'true'
}
row.append(render_macro_from_template(
name="render_record_authors",
template="inspirehep_theme/format/record/Inspire_Default_HTML_general_macros.tpl",
ctx=ctx
)
)
try:
row.append(hit.publication_info[0].journal_title)
except AttributeError:
row.append('')
try:
row.append(hit.citation_count)
except AttributeError:
row.append(0)
result.append(row)
return result, hits.total
def _get_preprint_context(record):
abstract = get_abstract(record)
try:
abstract_language = detect(abstract)
except LangDetectException:
abstract_language = ''
return {
'abstract': abstract,
'abstract_language': abstract_language,
'arxiv_id': get_arxiv_id(record),
'authors': get_authors(record),
'collaborations': get_collaborations(record),
'divulgation': get_divulgation(record),
'domains': get_domains(record),
'inspire_id': get_inspire_id(record),
'keywords': get_keywords(record),
'language': get_language(record),
'subtitle': get_subtitle(record),
'title': get_title(record),
}
def _get_comm_context(record):
abstract = get_abstract(record)
try:
abstract_language = detect(abstract)
except LangDetectException:
abstract_language = ''
conference_record = get_conference_record(record)
conference_city = get_conference_city(conference_record)
conference_country = get_conference_country(conference_record)
conference_end_date = get_conference_end_date(conference_record)
conference_start_date = get_conference_start_date(conference_record)
conference_title = get_conference_title(conference_record)
return {
'abstract': abstract,
'abstract_language': abstract_language,
'arxiv_id': get_arxiv_id(record),
'authors': get_authors(record),
'collaborations': get_collaborations(record),
'conference_city': conference_city,
'conference_country': conference_country,
'conference_end_date': conference_end_date,
'conference_start_date': conference_start_date,
'conference_title': conference_title,
'divulgation': get_divulgation(record),
'doi': get_doi(record),
'domains': get_domains(record),
'inspire_id': get_inspire_id(record),
'journal_issue': get_journal_issue(record),
'journal_title': get_journal_title(record),
'journal_volume': get_journal_volume(record),
'keywords': get_keywords(record),
'language': get_language(record),
'page_artid': get_page_artid(record),
'peer_reviewed': get_peer_reviewed(record),
'publication_date': get_publication_date(record),
'subtitle': get_subtitle(record),
'title': get_title(record),
}
def _get_art_context(record):
abstract = get_abstract(record)
abstract_language = langdetect.detect(abstract)
return {
'abstract': abstract,
'abstract_language': abstract_language,
'arxiv_id': get_arxiv_id(record),
'authors': get_authors(record),
'collaborations': get_collaborations(record),
'divulgation': get_divulgation(record),
'doi': get_doi(record),
'domain': get_domain(record),
'inspire_id': get_inspire_id(record),
'journal_issue': get_journal_issue(record),
'journal_title': get_journal_title(record),
'journal_volume': get_journal_volume(record),
'language': get_language(record),
'page_artid': get_page_artid(record),
'peer_reviewed': get_peer_reviewed(record),
'publication_date': get_publication_date(record),
'title': get_title(record),
}
def title(self):
"""Get preferred title."""
return get_title(self)
def title(self):
"""Get preferred title."""
return get_title(self)
def serialize(self, pid, record, links_factory=None):
"""
Serialize a single impact graph from a record.
:param pid: Persistent identifier instance.
:param record: Record instance.
:param links_factory: Factory function for the link generation,
which are added to the response.
"""
out = {}
# Add information about current record
out['inspire_id'] = record['control_number']
out['title'] = get_title(record)
out['year'] = record['earliest_date'].split('-')[0]
# Get citations
citations = []
record_citations = LiteratureSearch().query(
'match', references__recid=record['control_number'],
).params(
size=9999,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
).execute().hits
for citation in record_citations:
try:
citation_count = citation.citation_count
except AttributeError:
citation_count = 0
citations.append({
"inspire_id": citation['control_number'],
"citation_count": citation_count,
"title": get_title(citation.to_dict()),
"year": citation['earliest_date'].split('-')[0]
})
out['citations'] = citations
# Get references
record_references = record.get('references', [])
references = []
reference_recids = [
ref['recid'] for ref in record_references if ref.get('recid')
]
if reference_recids:
record_references = get_es_records(
'lit',
reference_recids,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
)
for reference in record_references:
try:
citation_count = reference.citation_count
except AttributeError:
citation_count = 0
references.append({
"inspire_id": reference['control_number'],
"citation_count": citation_count,
"title": get_title(reference),
"year": reference['earliest_date'].split('-')[0]
})
out['references'] = references
return json.dumps(out)
def publication_info(record):
"""Displays inline publication and conference information"""
result = {}
out = []
if 'publication_info' in record:
journal_title, journal_volume, year, journal_issue, pages = \
('', '', '', '', '')
for pub_info in record['publication_info']:
if 'journal_title' in pub_info:
journal_title = '<i>' + pub_info['journal_title'] + '</i>'
if 'journal_volume' in pub_info:
journal_volume = ' ' + pub_info['journal_volume']
if 'year' in pub_info:
year = ' (' + str(pub_info['year']) + ')'
if 'journal_issue' in pub_info:
journal_issue = ' ' + pub_info['journal_issue'] + ', '
if 'page_start' in pub_info and 'page_end' in pub_info:
pages = ' ' + '{page_start}-{page_end}'.format(**pub_info)
elif 'page_start' in pub_info:
pages = ' ' + '{page_start}'.format(**pub_info)
elif 'artid' in pub_info:
pages = ' ' + '{artid}'.format(**pub_info)
out.append(journal_title + journal_volume +
year + journal_issue + pages)
if out:
result['pub_info'] = out
if not result:
for field in record['publication_info']:
if 'pubinfo_freetext' in field:
out.append(field['pubinfo_freetext'])
result['pub_info'] = out
break
# Conference info line
for pub_info in record['publication_info']:
conference_recid = None
parent_recid = None
if 'conference_record' in pub_info:
conference_rec = replace_refs(pub_info['conference_record'],
'es')
if conference_rec and conference_rec.get('control_number'):
conference_recid = conference_rec['control_number']
if 'parent_record' in pub_info:
parent_rec = replace_refs(pub_info['parent_record'], 'es')
if parent_rec and parent_rec.get('control_number'):
parent_recid = parent_rec['control_number']
if conference_recid and parent_recid:
try:
ctx = {
"parent_recid": parent_recid,
"conference_recid": conference_recid,
"conference_title": get_title(conference_rec)
}
if result:
result['conf_info'] = render_macro_from_template(
name="conf_with_pub_info",
template="inspirehep_theme/format/record/Conference_info_macros.tpl",
ctx=ctx)
break
else:
ctx.update(dict(
page_start=pub_info.get('page_start'),
page_end=pub_info.get('page_end'),
artid=pub_info.get('artid')
))
result['conf_info'] = render_macro_from_template(
name="conf_without_pub_info",
template="inspirehep_theme/format/record/Conference_info_macros.tpl",
ctx=ctx)
break
except TypeError:
pass
elif conference_recid and not parent_recid:
try:
ctx = {
"conference_recid": conference_recid,
"conference_title": get_title(conference_rec),
"pub_info": bool(result.get('pub_info', ''))
}
result['conf_info'] = render_macro_from_template(
name="conference_only",
template="inspirehep_theme/format/record/Conference_info_macros.tpl",
ctx=ctx)
except TypeError:
pass
elif parent_recid and not conference_recid:
try:
ctx = {
"parent_recid": parent_recid,
"parent_title":
parent_rec['titles'][0]['title'].replace(
"Proceedings, ", "", 1),
"pub_info": bool(result.get('pub_info', ''))
}
result['conf_info'] = render_macro_from_template(
name="proceedings_only",
template="inspirehep_theme/format/record/Conference_info_macros.tpl",
ctx=ctx)
except TypeError:
pass
return result
def get_publications():
recid = request.values.get('recid', 0, type=int)
publications = []
collaborations = set()
keywords = set()
search = LiteratureSearch().query({
"match": {
"authors.recid": recid
}
}).params(_source=[
'accelerator_experiments', 'control_number', 'earliest_date',
'facet_inspire_doc_type', 'publication_info', 'titles',
'thesaurus_terms'
])
for result in search.scan():
try:
result_source = result.to_dict()
publication = {}
# Get publication title (required).
publication['title'] = get_title(result_source)
# Get publication recid (required).
publication['recid'] = result_source['control_number']
except (IndexError, KeyError):
continue
# Get publication type.
try:
publication['type'] = result_source.get('facet_inspire_doc_type',
[])[0]
except IndexError:
publication['type'] = "Not defined"
# Get journal title.
try:
publication['journal_title'] = result_source.get(
'publication_info', [])[0]['journal_title']
# Get journal recid.
try:
publication['journal_recid'] = result_source.get(
'publication_info', [])[0]['journal_recid']
except KeyError:
pass
except (IndexError, KeyError):
pass
# Get publication year.
try:
publication['year'] = result_source.get('publication_info',
[])[0]['year']
except (IndexError, KeyError):
pass
# Get keywords.
for keyword in result_source.get('thesaurus_terms', []):
if keyword.get('keyword') is not "* Automatic Keywords *" \
and keyword.get('keyword'):
keywords.add(keyword.get('keyword'))
# Get collaborations.
for experiment in result_source.get('accelerator_experiments', []):
collaborations.add(experiment.get('experiment'))
# Append to the list.
publications.append(publication)
response = {}
response['publications'] = publications
response['keywords'] = list(keywords)
response['collaborations'] = list(collaborations)
return jsonify(response)
def get_publications():
recid = request.values.get('recid', 0, type=int)
publications = []
collaborations = set()
keywords = set()
for result in scan(
current_search_client,
query={
'_source': ['accelerator_experiments',
'control_number',
'earliest_date',
'facet_inspire_doc_type',
'publication_info',
'titles',
'thesaurus_terms'
],
'query': {"match": {"authors.recid": recid}}
},
index='records-hep',
doc_type='hep'):
try:
result_source = result['_source']
publication = {}
# Get publication title (required).
publication['title'] = get_title(result_source)
# Get publication recid (required).
publication['recid'] = result_source['control_number']
except (IndexError, KeyError):
continue
# Get publication type.
try:
publication['type'] = result_source.get(
'facet_inspire_doc_type', [])[0]
except IndexError:
publication['type'] = "Not defined"
# Get journal title.
try:
publication['journal_title'] = result_source.get(
'publication_info', [])[0]['journal_title']
# Get journal recid.
try:
publication['journal_recid'] = result_source.get(
'publication_info', [])[0]['journal_recid']
except KeyError:
pass
except (IndexError, KeyError):
pass
# Get publication year.
try:
publication['year'] = result_source.get(
'publication_info', [])[0]['year']
except (IndexError, KeyError):
pass
# Get keywords.
for keyword in result_source.get('thesaurus_terms', []):
if keyword.get('keyword') is not "* Automatic Keywords *" \
and keyword.get('keyword'):
keywords.add(keyword.get('keyword'))
# Get collaborations.
for experiment in result_source.get(
'accelerator_experiments', []):
collaborations.add(experiment.get('experiment'))
# Append to the list.
publications.append(publication)
response = {}
response['publications'] = publications
response['keywords'] = list(keywords)
response['collaborations'] = list(collaborations)
return jsonify(response)
def serialize(self, pid, record, links_factory=None):
"""Return a list of publications for a given author recid.
:param pid:
Persistent identifier instance.
:param record:
Record instance.
:param links_factory:
Factory function for the link generation, which are added to
the response.
"""
author_pid = pid.pid_value
publications = []
search = LiteratureSearch().query({
"match": {
"authors.recid": author_pid
}
}).params(
_source=[
"accelerator_experiments",
"earliest_date",
"citation_count",
"control_number",
"facet_inspire_doc_type",
"publication_info",
"self",
"thesaurus_terms",
"titles",
]
)
for result in search.scan():
result_source = result.to_dict()
publication = {}
publication['id'] = int(result_source['control_number'])
publication['record'] = result_source['self']
publication['title'] = get_title(result_source)
# Get the earliest date.
try:
publication['date'] = result_source['earliest_date']
except KeyError:
pass
# Get publication type.
try:
publication['type'] = result_source.get(
'facet_inspire_doc_type', [])[0]
except IndexError:
pass
# Get citation count.
try:
publication['citations'] = result_source['citation_count']
except KeyError:
pass
# Get journal.
try:
publication['journal'] = {}
publication['journal']['title'] = result_source.get(
'publication_info', [])[0]['journal_title']
# Get journal id and $self.
try:
publication['journal']['id'] = result_source.get(
'publication_info', [])[0]['journal_recid']
publication['journal']['record'] = result_source.get(
'publication_info', [])[0]['journal_record']
except KeyError:
pass
except (IndexError, KeyError):
del publication['journal']
# Get collaborations.
collaborations = set()
for experiment in result_source.get('accelerator_experiments', []):
collaborations.add(experiment.get('experiment'))
if collaborations:
publication['collaborations'] = list(collaborations)
publications.append(publication)
return json.dumps(publications)
def title_rule(self, key, value):
title = get_title({"titles": value})
if title == '':
raise KeyError
subtitle = get_subtitle({"titles": value})
return {"title": title, "subtitle": subtitle}
def serialize(self, pid, record, links_factory=None):
"""Return a list of publications for a given author recid.
:param pid:
Persistent identifier instance.
:param record:
Record instance.
:param links_factory:
Factory function for the link generation, which are added to
the response.
"""
author_pid = pid.pid_value
publications = []
search = LiteratureSearch().query({
"match": {
"authors.recid": author_pid
}
}).params(
_source=[
"accelerator_experiments",
"earliest_date",
"citation_count",
"control_number",
"facet_inspire_doc_type",
"publication_info",
"self",
"keywords",
"titles",
]
)
for result in search.scan():
result_source = result.to_dict()
publication = {}
publication['id'] = int(result_source['control_number'])
publication['record'] = result_source['self']
publication['title'] = get_title(result_source)
# Get the earliest date.
try:
publication['date'] = result_source['earliest_date']
except KeyError:
pass
# Get publication type.
try:
publication['type'] = result_source.get(
'facet_inspire_doc_type', [])[0]
except IndexError:
pass
# Get citation count.
try:
publication['citations'] = result_source['citation_count']
except KeyError:
pass
# Get journal.
try:
publication['journal'] = {}
publication['journal']['title'] = result_source.get(
'publication_info', [])[0]['journal_title']
# Get journal id and $self.
try:
publication['journal']['id'] = result_source.get(
'publication_info', [])[0]['journal_recid']
publication['journal']['record'] = result_source.get(
'publication_info', [])[0]['journal_record']
except KeyError:
pass
except (IndexError, KeyError):
del publication['journal']
# Get collaborations.
collaborations = set()
for experiment in result_source.get('accelerator_experiments', []):
collaborations.add(experiment.get('experiment'))
if collaborations:
publication['collaborations'] = list(collaborations)
publications.append(publication)
return json.dumps(publications)
def get_publications():
recid = request.values.get("recid", 0, type=int)
publications = []
collaborations = set()
keywords = set()
for result in scan(
current_search_client,
query={
"_source": [
"accelerator_experiments",
"control_number",
"earliest_date",
"facet_inspire_doc_type",
"publication_info",
"titles",
"thesaurus_terms",
],
"query": {"match": {"authors.recid": recid}},
},
index="records-hep",
doc_type="hep",
):
try:
result_source = result["_source"]
publication = {}
# Get publication title (required).
publication["title"] = get_title(result_source)
# Get publication recid (required).
publication["recid"] = result_source["control_number"]
except (IndexError, KeyError):
continue
# Get publication type.
try:
publication["type"] = result_source.get("facet_inspire_doc_type", [])[0]
except IndexError:
publication["type"] = "Not defined"
# Get journal title.
try:
publication["journal_title"] = result_source.get("publication_info", [])[0]["journal_title"]
# Get journal recid.
try:
publication["journal_recid"] = result_source.get("publication_info", [])[0]["journal_recid"]
except KeyError:
pass
except (IndexError, KeyError):
pass
# Get publication year.
try:
publication["year"] = result_source.get("publication_info", [])[0]["year"]
except (IndexError, KeyError):
pass
# Get keywords.
for keyword in result_source.get("thesaurus_terms", []):
if keyword.get("keyword") is not "* Automatic Keywords *" and keyword.get("keyword"):
keywords.add(keyword.get("keyword"))
# Get collaborations.
for experiment in result_source.get("accelerator_experiments", []):
collaborations.add(experiment.get("experiment"))
# Append to the list.
publications.append(publication)
response = {}
response["publications"] = publications
response["keywords"] = list(keywords)
response["collaborations"] = list(collaborations)
return jsonify(response)
def serialize(self, pid, record, links_factory=None):
"""
Serialize a single impact graph from a record.
:param pid: Persistent identifier instance.
:param record: Record instance.
:param links_factory: Factory function for the link generation,
which are added to the response.
"""
out = {}
# Add information about current record
out['inspire_id'] = record['control_number']
out['title'] = get_title(record)
out['year'] = record['earliest_date'].split('-')[0]
# Get citations
citations = []
record_citations = LiteratureSearch().query_from_iq(
'refersto:' + str(record['control_number'])
).params(
size=9999,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
).execute().hits
for citation in record_citations:
try:
citation_count = citation.citation_count
except AttributeError:
citation_count = 0
citations.append({
"inspire_id": citation['control_number'],
"citation_count": citation_count,
"title": get_title(citation.to_dict()),
"year": citation['earliest_date'].split('-')[0]
})
out['citations'] = citations
# Get references
record_references = record.get('references', [])
references = []
reference_recids = [
ref['recid'] for ref in record_references if ref.get('recid')
]
if reference_recids:
record_references = get_es_records(
'lit',
reference_recids,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
)
for reference in record_references:
try:
citation_count = reference.citation_count
except AttributeError:
citation_count = 0
references.append({
"inspire_id": reference['control_number'],
"citation_count": citation_count,
"title": get_title(reference),
"year": reference['earliest_date'].split('-')[0]
})
out['references'] = references
return json.dumps(out)
def serialize(self, pid, record, links_factory=None):
"""
Serialize a single impact graph from a record.
:param pid: Persistent identifier instance.
:param record: Record instance.
:param links_factory: Factory function for the link generation,
which are added to the response.
"""
out = {}
# Add information about current record
out['inspire_id'] = record['control_number']
out['title'] = get_title(record)
out['year'] = record['earliest_date'].split('-')[0]
# Get citations
citations = []
es_query = IQ('refersto:' + record['control_number'])
record_citations = current_search_client.search(
index='records-hep',
doc_type='hep',
body={"query": es_query.to_dict()},
size=9999,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
)['hits']['hits']
for citation in record_citations:
citation = citation['_source']
citations.append({
"inspire_id": citation['control_number'],
"citation_count": citation.get('citation_count', 0),
"title": get_title(citation),
"year": citation['earliest_date'].split('-')[0]
})
out['citations'] = citations
# Get references
record_references = record.get('references', [])
references = []
reference_recids = [
ref['recid'] for ref in record_references if ref.get('recid')
]
if reference_recids:
query = IQ(' OR '.join('recid:' + str(ref)
for ref in reference_recids))
record_references = current_search_client.search(
index='records-hep',
doc_type='hep',
body={"query": query.to_dict()},
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
)
for reference in record_references['hits']['hits']:
ref_info = reference["_source"]
references.append({
"inspire_id": ref_info['control_number'],
"citation_count": ref_info.get('citation_count', 0),
"title": get_title(ref_info),
"year": ref_info['earliest_date'].split('-')[0]
})
out['references'] = references
return json.dumps(out)
def serialize(self, pid, record, links_factory=None):
"""
Serialize a single impact graph from a record.
:param pid: Persistent identifier instance.
:param record: Record instance.
:param links_factory: Factory function for the link generation,
which are added to the response.
"""
out = {}
# Add information about current record
out['inspire_id'] = record['control_number']
out['title'] = get_title(record)
out['year'] = record['earliest_date'].split('-')[0]
# Get citations
citations = []
es_query = Query('refersto:' + record['control_number'])
es_query.body.update({'size': 9999})
record_citations = current_search_client.search(index='records-hep',
doc_type='hep',
body=es_query.body,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
])['hits']['hits']
for citation in record_citations:
citation = citation['_source']
citations.append({
"inspire_id":
citation['control_number'],
"citation_count":
citation.get('citation_count', 0),
"title":
get_title(citation),
"year":
citation['earliest_date'].split('-')[0]
})
out['citations'] = citations
# Get references
record_references = record.get('references', [])
references = []
reference_recids = [
ref['recid'] for ref in record_references if ref.get('recid')
]
if reference_recids:
mget_body = {"ids": reference_recids}
record_references = current_search_client.mget(
index='records-hep',
doc_type='hep',
body=mget_body,
_source=[
'control_number', 'citation_count', 'titles',
'earliest_date'
])
for reference in record_references["docs"]:
ref_info = reference["_source"]
references.append({
"inspire_id":
ref_info['control_number'],
"citation_count":
ref_info.get('citation_count', 0),
"title":
get_title(ref_info),
"year":
ref_info['earliest_date'].split('-')[0]
})
out['references'] = references
return json.dumps(out)
