def test_get_value(double_title, single_title, empty_title):
"""Test get_value utility"""
assert len(get_value(double_title, "titles.title")) == 2
assert get_value(double_title, "titles.title[0]") == "Parton distributions with LHC data"
assert get_value(single_title, "titles.title") == ["The Large Hadron Collider"]
assert get_value(empty_title, "titles.title") == []
assert get_value(empty_title, "foo", {}) == {}
def _match_with_invenio_matcher(obj, eng):
from invenio_matcher.api import match as _match
if queries is None:
queries_ = [{"type": "exact", "match": "dois.value"}, {"type": "exact", "match": "arxiv_eprints.value"}]
else:
queries_ = queries
record_matches = {
"recids": [],
"records": [],
"base_url": os.path.join(current_app.config["SERVER_NAME"], "record"),
}
record = {}
record["dois.value"] = get_value(obj.data, "dois.value")
record["arxiv_eprints.value"] = get_value(obj.data, "arxiv_eprints.value")
for matched_record in _match(record, queries=queries_, index=index, doc_type=doc_type):
matched_recid = matched_record.record.get("id")
record_matches["recids"].append(matched_recid)
record_matches["records"].append({"source": matched_record.record.dumps(), "score": matched_record.score})
if len(record_matches["recids"]) > 0:
obj.extra_data["record_matches"] = record_matches
return True
return False
def curation_ticket_context(user, obj):
recid = obj.extra_data.get('recid')
record_url = obj.extra_data.get('url')
arxiv_ids = get_value(obj.data, 'arxiv_eprints.value') or []
for index, arxiv_id in enumerate(arxiv_ids):
if arxiv_id and is_arxiv_post_2007(arxiv_id):
arxiv_ids[index] = 'arXiv:{0}'.format(arxiv_id)
report_numbers = get_value(obj.data, 'report_numbers.value') or []
dois = [
"doi:{0}".format(doi)
for doi in get_value(obj.data, 'dois.value') or []
]
link_to_pdf = obj.extra_data.get('submission_data').get('pdf')
subject = ' '.join(
filter(lambda x: x is not None,
arxiv_ids + dois + report_numbers + ['(#{0})'.format(recid)]))
references = obj.extra_data.get('submission_data').get('references')
user_comment = obj.extra_data.get('submission_data').get('extra_comments')
return dict(recid=recid,
record_url=record_url,
link_to_pdf=link_to_pdf,
email=user.email,
references=references,
user_comment=user_comment,
subject=subject)
def get_description(obj):
"""Get the description column part."""
if not isinstance(obj.data, dict):
return "No description found."
abstract = ""
authors = []
categories = []
final_identifiers = []
# Get identifiers
dois = get_value(obj.data, "dois.value", [])
if dois:
final_identifiers.extend(dois)
system_no = get_value(obj.data, "external_system_numbers.value", [])
if system_no:
final_identifiers.extend(system_no)
# Get subject categories, adding main one first. Order matters here.
record_categories = get_value(obj.data, "arxiv_eprints.categories", []) + \
get_value(obj.data, "subject_terms.term", [])
for category_list in record_categories:
if isinstance(category_list, list):
categories.extend(category_list)
else:
categories.append(category_list)
categories = list(OrderedDict.fromkeys(categories)) # Unique only
abstract = get_value(obj.data, "abstracts.value", [""])[0]
authors = obj.data.get("authors", [])
return render_template('inspire_workflows/styles/harvesting_record.html',
object=obj,
authors=authors,
categories=categories,
abstract=abstract,
identifiers=final_identifiers)
def curation_ticket_context(user, obj):
recid = obj.extra_data.get('recid')
record_url = obj.extra_data.get('url')
arxiv_ids = get_value(obj.data, 'arxiv_eprints.value') or []
for index, arxiv_id in enumerate(arxiv_ids):
if arxiv_id and is_arxiv_post_2007(arxiv_id):
arxiv_ids[index] = 'arXiv:{0}'.format(arxiv_id)
report_numbers = get_value(obj.data, 'report_numbers.value') or []
dois = [
"doi:{0}".format(doi)
for doi in get_value(obj.data, 'dois.value') or []
]
link_to_pdf = obj.extra_data.get('formdata', {}).get('url')
subject = ' '.join(filter(
lambda x: x is not None,
arxiv_ids + dois + report_numbers + ['(#{0})'.format(recid)]
))
references = obj.extra_data.get('formdata').get('references')
user_comment = obj.extra_data.get('formdata', {}).get('extra_comments', '')
return dict(
recid=recid,
record_url=record_url,
link_to_pdf=link_to_pdf,
email=user.email,
references=references,
user_comment=user_comment,
subject=subject
)
def prepare_magpie_payload(record, corpus):
"""Prepare payload to send to Magpie API."""
payload = dict(text="", corpus=corpus)
titles = filter(None, get_value(record, "titles.title", []))
abstracts = filter(None, get_value(record, "abstracts.value", []))
payload["text"] = ". ".join(
[part.encode('utf-8') for part in titles + abstracts])
return payload
def prepare_magpie_payload(record, corpus):
"""Prepare payload to send to Magpie API."""
payload = dict(text="", corpus=corpus)
titles = filter(None, get_value(record, "titles.title", []))
abstracts = filter(None, get_value(record, "abstracts.value", []))
payload["text"] = ". ".join(
[part.encode('utf-8') for part in titles + abstracts])
return payload
def _structure_data(struct):
return {
'type': get_value(struct, "collections[1].primary", "").lower(),
# ^^ FIXME: This may not be one of the HAL accepted values:
# institution, department, laboratory or researchteam
'name': get_value(struct, "institution[0]", ""),
'address': get_value(struct, "address[0].original_address", []),
'country': get_value(struct, "address[0].country_code", ""),
'recid': get_recid_from_ref(struct['self']),
}
def _structure_data(struct):
return {
'type': get_value(struct, "collections[1].primary", "").lower(),
# ^^ FIXME: This may not be one of the HAL accepted values:
# institution, department, laboratory or researchteam
'name': get_value(struct, "institution[0]", ""),
'address': get_value(struct, "address[0].original_address", []),
'country': get_value(struct, "address[0].country_code", ""),
'recid': get_recid_from_ref(struct['self']),
}
def _get_wfs_same_source(obj, eng):
current_source = get_value(obj.data, 'acquisition_source.source').lower()
try:
workflows = obj.extra_data[extra_data_key]
except KeyError:
workflows = []
for wf_id in workflows:
wf = workflow_object_class.get(wf_id)
wf_source = get_value(wf.data, 'acquisition_source.source').lower()
if wf_source == current_source:
return True
return False
def _get_wfs_same_source(obj, eng):
current_source = get_value(obj.data, 'acquisition_source.source').lower()
try:
workflows = obj.extra_data[extra_data_key]
except KeyError:
workflows = []
for wf_id in workflows:
wf = workflow_object_class.get(wf_id)
wf_source = get_value(wf.data, 'acquisition_source.source').lower()
if wf_source == current_source:
return True
return False
def is_experimental_paper(obj, eng):
"""Check if the record is an experimental paper."""
categories = list(get_value(obj.data, "arxiv_eprints.categories", [[]])[0]) + \
list(get_value(obj.data, "field_categories.term", []))
categories_to_check = [
"hep-ex", "nucl-ex", "astro-ph", "astro-ph.IM", "astro-ph.CO",
"astro-ph.EP", "astro-ph.GA", "astro-ph.HE", "astro-ph.SR",
"physics.ins-det",
"Experiment-HEP", "Experiment-Nucl", "Astrophysics", "Instrumentation"
]
for experimental_category in categories_to_check:
if experimental_category in categories:
return True
return False
def is_experimental_paper(obj, eng):
"""Check if the record is an experimental paper."""
categories = list(get_value(obj.data, "arxiv_eprints.categories", [[]])[0]) + \
list(get_value(obj.data, "field_categories.term", []))
categories_to_check = [
"hep-ex", "nucl-ex", "astro-ph", "astro-ph.IM", "astro-ph.CO",
"astro-ph.EP", "astro-ph.GA", "astro-ph.HE", "astro-ph.SR",
"physics.ins-det",
"Experiment-HEP", "Experiment-Nucl", "Astrophysics", "Instrumentation"
]
for experimental_category in categories_to_check:
if experimental_category in categories:
return True
return False
def populate_inspire_subjects(sender, json, *args, **kwargs):
"""Populate the INSPIRE subjects before indexing.
Adds the `facet_inspire_subjects` key to the record, to be used for
faceting in the search interface.
"""
json['facet_inspire_subjects'] = get_value(json, 'inspire_categories.term')
def get_subject(record):
inspire_categories = force_force_list(
get_value(record, 'inspire_categories'))
terms = [ic['term'] for ic in inspire_categories if ic.get('term')]
if terms:
return terms[0]
def _conference_data(conf):
ref = replace_refs(conf, 'db')
# FIXME: Add conference city, country, and country code fields
if ref:
return {'type': "conference",
'name': get_value(ref, "titles[0].title", ""),
'acronym': get_value(ref, "acronym[0]", ""),
'opening_date': get_value(ref, "opening_date", ""),
'closing_date': get_value(ref, "closing_date", "")}
else:
return {'type': "conference",
'name': "",
'acronym': "",
'opening_date': "",
'closing_date': ""}
def test_get_value_returns_single_title():
empty_titles = InspireRecord({'titles': []})
expected = []
result = get_value(empty_titles, "titles.title")
assert expected == result
def populate_inspire_subjects(sender, json, *args, **kwargs):
"""Populate the INSPIRE subjects before indexing.
Adds the `facet_inspire_subjects` key to the record, to be used for
faceting in the search interface.
"""
json['facet_inspire_subjects'] = get_value(json, 'inspire_categories.term')
def prepare_payload(record):
"""Prepare payload to send to Beard API."""
payload = dict(title="", abstract="", categories=[])
titles = filter(None, get_value(record, "titles.title", []))
# FIXME May have to normalize categories in the future
arxiv_categories = map(
lambda x: x[0],
filter(None, get_value(record, "arxiv_eprints.categories", [])))
if titles:
payload['title'] = titles[0]
abstracts = filter(None, get_value(record, "abstracts.value", []))
if abstracts:
payload['abstract'] = abstracts[0]
if arxiv_categories:
payload['categories'] = arxiv_categories
return payload
def test_get_value_returns_empty_dic_when_there_are_no_titles():
empty_titles = InspireRecord({'titles': []})
expected = {}
result = get_value(empty_titles, "foo")
assert expected == result
def newreview():
"""View for INSPIRE author new form review by a cataloger."""
objectid = request.values.get('objectid', 0, type=int)
if not objectid:
abort(400)
workflow_metadata = WorkflowUIRecord.get_record(objectid)['metadata']
# Converting json to populate form
workflow_metadata['extra_comments'] = get_value(
workflow_metadata,
'_private_notes[0].value'
)
convert_for_form(workflow_metadata)
form = AuthorUpdateForm(
data=workflow_metadata, is_review=True)
ctx = {
"action": url_for('.reviewhandler', objectid=objectid),
"name": "authorUpdateForm",
"id": "authorUpdateForm",
"objectid": objectid
}
return render_template('authors/forms/review_form.html', form=form, **ctx)
def test_get_value_returns_single_title():
empty_titles = Record({'titles': []})
expected = []
result = get_value(empty_titles, "titles.title")
assert expected == result
def test_get_value_returns_empty_dic_when_there_are_no_titles():
empty_titles = Record({'titles': []})
expected = {}
result = get_value(empty_titles, "foo")
assert expected == result
def references(self, key, value):
"""Produce list of references."""
value = force_force_list(value)
def get_value(value):
# Retrieve fields as described here:
# https://twiki.cern.ch/twiki/bin/view/Inspire/DevelopmentRecordMarkup.
rb = ReferenceBuilder()
mapping = [('o', rb.set_number), ('m', rb.add_misc),
('x', partial(rb.add_raw_reference, source='dojson')),
('1', rb.set_texkey), ('u', rb.add_url),
('r', rb.add_report_number), ('s', rb.set_pubnote),
('p', rb.set_publisher), ('y', rb.set_year),
('i', rb.add_uid), ('b', rb.add_uid), ('a', rb.add_uid),
('c', rb.add_collaboration), ('q', rb.add_title),
('t', rb.add_title), ('h', rb.add_refextract_authors_str),
('e', partial(rb.add_author, role='ed.'))]
for field, method in mapping:
for element in force_force_list(value.get(field)):
if element:
method(element)
if '0' in value:
recid = get_int_value(value, '0')
rb.set_record(get_record_ref(recid, 'literature'))
return rb.obj
references = self.get('references', [])
references.extend(get_value(v) for v in value)
return references
def populate_experiment_suggest(sender, json, *args, **kwargs):
"""Populates experiment_suggest field of experiment records."""
# FIXME: Use a dedicated method when #1355 will be resolved.
if 'experiments.json' in json.get('$schema'):
experiment_names = get_value(json, 'experiment_names.title')
title_variants = force_list(
get_value(json, 'title_variants.title'))
json.update({
'experiment_suggest': {
'input': experiment_names + title_variants,
'output': experiment_names[0],
'payload': {'$ref': get_value(json, 'self.$ref')},
},
})
def is_arxiv_paper(obj, *args, **kwargs):
"""Check if the record is from arXiv."""
arxiv_id = get_arxiv_id(obj.data)
categories = get_value(obj.data, 'arxiv_eprints.categories')
if arxiv_id or categories:
return True
return False
def _was_not_published(json):
def _not_published(publication_info):
return 'page_start' not in publication_info and 'artid' not in publication_info
publication_infos = force_force_list(get_value(json, 'publication_info'))
not_published = map(_not_published, publication_infos)
return all(not_published)
def is_arxiv_paper(obj, *args, **kwargs):
"""Check if the record is from arXiv."""
arxiv_id = get_clean_arXiv_id(obj.data)
categories = get_value(obj.data, 'arxiv_eprints.categories')
if arxiv_id or categories:
return True
return False
def thesis_supervisors2marc(self, key, value):
"""Thesis supervisors.
FIXME: handle recids to 701__z."""
return {
'a': value.get('full_name'),
'u': get_value(value, 'affiliations.value'),
}
def prepare_payload(record):
"""Prepare payload to send to Beard API."""
payload = dict(title="", abstract="", categories=[])
titles = filter(None, get_value(record, "titles.title", []))
# FIXME May have to normalize categories in the future
arxiv_categories = map(
lambda x: x[0],
filter(None, get_value(record, "arxiv_eprints.categories", []))
)
if titles:
payload['title'] = titles[0]
abstracts = filter(None, get_value(record, "abstracts.value", []))
if abstracts:
payload['abstract'] = abstracts[0]
if arxiv_categories:
payload['categories'] = arxiv_categories
return payload
def get_title(cls, obj, **kwargs):
"""Return the value to put in the title column of Holding Pen."""
if isinstance(obj.data, dict):
titles = filter(None, get_value(obj.data, "titles.title", []))
if titles:
# Show first title that evaluates to True
return titles[0]
return "No title available"
def populate_experiment_suggest(sender, json, *args, **kwargs):
"""Populates experiment_suggest field of experiment records."""
# FIXME: Use a dedicated method when #1355 will be resolved.
if 'experiments.json' in json.get('$schema'):
experiment_names = get_value(json, 'experiment_names.title')
title_variants = force_force_list(
get_value(json, 'title_variants.title'))
json.update({
'experiment_suggest': {
'input': experiment_names + title_variants,
'output': experiment_names[0],
'payload': {
'$ref': get_value(json, 'self.$ref')
},
},
})
def _get_author(self):
"""Return list of name(s) of the author(s)."""
def _is_supervisor(author):
contributor_roles = force_force_list(get_value(author, "contributor_roles.value"))
return "Supervision" in contributor_roles
result = []
spacinginitials = re.compile(r"([A-Z][a-z]{0,1}[}]?\.)(\b|[-\{])")
authors = force_force_list(get_value(self.record, "authors"))
non_supervisors = [el for el in authors if not _is_supervisor(el)]
result.extend([spacinginitials.sub(r"\1 \2", el["full_name"]) for el in non_supervisors if "full_name" in el])
corporate_authors = force_force_list(get_value(self.record, "corporate_author"))
result.extend(corporate_authors)
return result
def _parse_authors(record):
authors = get_value(record, "authors", [])
for author in authors:
try:
parsed = HumanName(author['full_name'])
author['parsed_name'] = parsed
except KeyError:
continue
return authors
def _parse_authors(record):
authors = get_value(record, "authors", [])
for author in authors:
try:
parsed = HumanName(author['full_name'])
author['parsed_name'] = parsed
except KeyError:
continue
return authors
def test_get_value_returns_none_on_index_error():
single_title = InspireRecord({
'titles': [{
'title':
'Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia',
}],
})
assert get_value(single_title, 'titles.title[1]') is None
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(category['a'])
return record
def _lookup(record, value):
"""Searches a key in a record.
Uses `get_value` to lookup a key in a JSON record, and
raises a `KeyError` if it wasn't found.
"""
result = get_value(record, value)
if not result:
raise KeyError
return result
def test_get_value_returns_none_on_index_error():
single_title = Record({
'titles': [
{
'title': 'Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia',
}
],
})
assert get_value(single_title, 'titles.title[1]') is None
def match_by_doi(record):
"""Match by DOIs."""
dois = get_value(record, 'dois.value', [])
result = set()
for doi in dois:
query = '0247:"{0}"'.format(doi)
result.update(search(query))
return list(result)
def _lookup(record, value):
"""Searches a key in a record.
Uses `get_value` to lookup a key in a JSON record, and
raises a `KeyError` if it wasn't found.
"""
result = get_value(record, value)
if not result:
raise KeyError
return result
def was_already_harvested(record):
"""Return True if the record was already harvested.
We use the following heuristic: if the record belongs to one of the
CORE categories then it was probably ingested in some other way.
"""
categories = get_value(record, 'inspire_categories.term', [])
for category in categories:
if category.lower() in current_app.config.get('INSPIRE_ACCEPTED_CATEGORIES', []):
return True
def match_by_doi(record):
"""Match by DOIs."""
dois = get_value(record, "dois.value", [])
result = set()
for doi in dois:
query = '0247:"{0}"'.format(doi)
result.update(search(query))
return list(result)
def was_already_harvested(record):
"""Return True if the record was already harvested.
We use the following heuristic: if the record belongs to one of the
CORE categories then it was probably ingested in some other way.
"""
categories = get_value(record, "field_categories.term", [])
for category in categories:
if category.lower() in current_app.config.get("INSPIRE_ACCEPTED_CATEGORIES", []):
return True
def _get_hep_record_brief(hep_record):
brief = {
'control_number': hep_record['control_number'],
'title': get_value(hep_record, 'titles[0].title'),
}
abstract = get_value(hep_record, 'abstracts[0].value')
if abstract is not None:
brief['abstract'] = abstract
arxiv_eprint = get_value(hep_record, 'arxiv_eprints[0].value')
if arxiv_eprint is not None:
brief['arxiv_eprint'] = arxiv_eprint
number_of_pages = get_value(hep_record, 'number_of_pages')
if number_of_pages is not None:
brief['number_of_pages'] = number_of_pages
earliest_date = get_value(hep_record, 'earliest_date')
if earliest_date is not None:
brief['earliest_date'] = earliest_date
authors = hep_record.get('authors')
if authors is not None:
brief['authors_count'] = len(authors)
author_briefs = []
for author in authors[:3]:
author_briefs.append({'full_name': author['full_name']})
brief['authors'] = author_briefs
public_notes = hep_record.get('public_notes')
if public_notes is not None:
public_notes_value = []
for public_note in public_notes:
public_notes_value.append({'value': public_note['value']})
brief['public_notes'] = public_notes_value
publication_info = hep_record.get('publication_info')
if publication_info is not None:
brief['publication_info'] = publication_info
return brief
def _match_with_invenio_matcher(obj, eng):
from invenio_matcher.api import match as _match
if queries is None:
queries_ = [
{'type': 'exact', 'match': 'dois.value'},
{'type': 'exact', 'match': 'arxiv_eprints.value'}
]
else:
queries_ = queries
record_matches = {
"recids": [],
"records": [],
"base_url": os.path.join(
current_app.config["SERVER_NAME"],
'record'
)
}
record = {}
record['dois.value'] = get_value(obj.data, 'dois.value')
record['arxiv_eprints.value'] = get_value(
obj.data, 'arxiv_eprints.value'
)
for matched_record in _match(
record,
queries=queries_,
index=index,
doc_type=doc_type
):
matched_recid = matched_record.record.get('id')
record_matches['recids'].append(matched_recid)
record_matches['records'].append({
"source": matched_record.record.dumps(),
"score": matched_record.score
})
if len(record_matches['recids']) > 0:
obj.extra_data["record_matches"] = record_matches
return True
return False
def _match_with_invenio_matcher(obj, eng):
from invenio_matcher.api import match as _match
if queries is None:
queries_ = [
{'type': 'exact', 'match': 'dois.value'},
{'type': 'exact', 'match': 'arxiv_eprints.value'}
]
else:
queries_ = queries
record_matches = {
"recids": [],
"records": [],
"base_url": os.path.join(
current_app.config["SERVER_NAME"],
'record'
)
}
record = {}
record['dois.value'] = get_value(obj.data, 'dois.value')
record['arxiv_eprints.value'] = get_value(
obj.data, 'arxiv_eprints.value'
)
for matched_record in _match(
record,
queries=queries_,
index=index,
doc_type=doc_type
):
matched_recid = matched_record.record.get('id')
record_matches['recids'].append(matched_recid)
record_matches['records'].append({
"source": matched_record.record.dumps(),
"score": matched_record.score
})
if len(record_matches['recids']) > 0:
obj.extra_data["record_matches"] = record_matches
return True
return False
def _conference_data(conf):
ref = replace_refs(conf, 'db')
# FIXME: Add conference city, country, and country code fields
if ref:
return {
'type': "conference",
'name': get_value(ref, "titles[0].title", ""),
'acronym': get_value(ref, "acronym[0]", ""),
'opening_date': get_value(ref, "opening_date", ""),
'closing_date': get_value(ref, "closing_date", "")
}
else:
return {
'type': "conference",
'name': "",
'acronym': "",
'opening_date': "",
'closing_date': ""
}
def thesis_supervisors2marc(self, key, value):
"""Thesis supervisors.
FIXME: handle recids to 701__z."""
_is_supervisor = 'Supervision' in value.get('contributor_roles', [])
if _is_supervisor:
return {
'a': value.get('full_name'),
'u': get_value(value, 'affiliations.value'),
}
def thesis_supervisors2marc(self, key, value):
"""Thesis supervisors.
FIXME: handle recids to 701__z."""
_is_supervisor = 'Supervision' in value.get('contributor_roles', [])
if _is_supervisor:
return {
'a': value.get('full_name'),
'u': get_value(value, 'affiliations.value'),
}
def test_get_value_allows_indexes_in_paths():
record = {
'titles': [
{'title': 'first title'},
{'title': 'second title'},
],
}
expected = 'second title'
result = get_value(record, 'titles.title[1]')
assert expected == result
def _get_author(self):
"""Return list of name(s) of the author(s)."""
def _is_supervisor(author):
contributor_roles = force_force_list(
get_value(author, 'contributor_roles.value'))
return 'Supervision' in contributor_roles
result = []
spacinginitials = re.compile(r'([A-Z][a-z]{0,1}[}]?\.)(\b|[-\{])')
authors = force_force_list(get_value(self.record, 'authors'))
non_supervisors = [el for el in authors if not _is_supervisor(el)]
result.extend(
[spacinginitials.sub(r'\1 \2', el['full_name'])
for el in non_supervisors if 'full_name' in el])
corporate_authors = force_force_list(
get_value(self.record, 'corporate_author'))
result.extend(corporate_authors)
return result
def _get_author(self):
"""Return list of name(s) of the author(s)."""
def _is_supervisor(author):
contributor_roles = force_list(
get_value(author, 'contributor_roles.value'))
return 'Supervision' in contributor_roles
result = []
spacinginitials = re.compile(r'([A-Z][a-z]{0,1}[}]?\.)(\b|[-\{])')
authors = force_list(get_value(self.record, 'authors'))
non_supervisors = [el for el in authors if not _is_supervisor(el)]
result.extend(
[spacinginitials.sub(r'\1 \2', el['full_name'])
for el in non_supervisors if 'full_name' in el])
corporate_authors = force_list(
get_value(self.record, 'corporate_author'))
result.extend(corporate_authors)
return result
def new_ticket_context(user, obj):
"""Context for literature new tickets."""
title = get_title(obj.data)
subject = "Your suggestion to INSPIRE: {0}".format(title)
user_comment = obj.extra_data.get('submission_data').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("submission_data",
{}).get("references"),
object=obj,
subject=subject)
def test_get_value_returns_the_two_titles():
double_title = Record({
"titles": [{
"title":
"Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia"
}, {
"title": "Monte Carlo tuning in the presence of Matching"
}],
})
expected = 2
result = len(get_value(double_title, "titles.title"))
assert expected == result
def test_get_value_returns_the_selected_title():
double_title = InspireRecord({
"titles": [{
"title":
"Importance of a consistent choice of alpha(s) in the matching of AlpGen and Pythia"
}, {
"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_value(double_title, "titles.title[0]")
assert expected == result
def test_references_can_be_updated(app, records_to_be_merged):
merged_record = get_db_record('lit', 111)
deleted_record = get_db_record('lit', 222)
deleted_record.merge(merged_record)
update_refs.delay('http://localhost:5000/api/literature/222',
'http://localhost:5000/api/literature/111')
pointing_record = get_db_record('lit', 333)
expected = 'http://localhost:5000/api/literature/111'
result = get_value(pointing_record,
'accelerator_experiments[0].record.$ref')
assert expected == result
def add_inspire_category(record, blob):
if not record.get('arxiv_eprints') or record.get('inspire_categories'):
return record
record.setdefault('inspire_categories', [])
for arxiv_category in get_value(record,
'arxiv_eprints.categories',
default=[]):
inspire_category = classify_field(arxiv_category)
if inspire_category:
record['inspire_categories'].append({
'term': inspire_category,
'source': 'arxiv',
})
return record
def pending_in_holding_pen(obj, eng):
"""Check if a record exists in HP by looking in given KB."""
from elasticsearch_dsl import Q
from invenio_db import db
from invenio_search import RecordsSearch
from invenio_workflows.models import WorkflowObjectModel, ObjectStatus
config = current_app.config['WORKFLOWS_UI_REST_ENDPOINT']
index = config.get('search_index')
doc_type = config.get('search_type')
searcher = RecordsSearch(
index=index, doc_type=doc_type
).params(version=True)
identifiers = []
for field, lookup in six.iteritems(
current_app.config.get("HOLDING_PEN_MATCH_MAPPING", {})):
# Add quotes around to make the search exact
identifiers += ['{0}:"{1}"'.format(field, i)
for i in get_value(obj.data, lookup, [])]
# Search for any existing record in Holding Pen, exclude self
if identifiers:
search = searcher.query(Q('query_string',
query=" OR ".join(identifiers),
allow_leading_wildcard=False))
search_result = search.execute()
id_list = [int(hit.id) for hit in search_result.hits]
matches_excluding_self = set(id_list) - set([obj.id])
if matches_excluding_self:
obj.extra_data["holdingpen_ids"] = list(matches_excluding_self)
pending_records = db.session.query(
WorkflowObjectModel
).with_entities(WorkflowObjectModel.id).filter(
WorkflowObjectModel.status != ObjectStatus.COMPLETED,
WorkflowObjectModel.id.in_(matches_excluding_self)
).all()
if pending_records:
pending_ids = [o[0] for o in pending_records]
obj.extra_data['pending_holdingpen_ids'] = pending_ids
obj.log.info(
"Pending records already found in Holding Pen ({0})"
.format(
pending_ids
)
)
return True
return False
