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 if user else '',
references=references,
user_comment=user_comment,
subject=subject)
def arxiv_eprints2marc(self, key, values):
"""Populate the ``037`` MARC field.
Also populates the ``035`` and the ``65017`` MARC fields through side effects.
"""
result_037 = self.get('037', [])
result_035 = self.get('035', [])
result_65017 = self.get('65017', [])
for value in values:
arxiv_id = value.get('value')
arxiv_id = 'arXiv:' + arxiv_id if is_arxiv_post_2007(
arxiv_id) else arxiv_id
result_037.append({
'9': 'arXiv',
'a': arxiv_id,
'c': force_single_element(value.get('categories')),
})
result_035.append({
'9': 'arXiv',
'a': 'oai:arXiv.org:' + value.get('value'),
})
categories = force_list(value.get('categories'))
for category in categories:
result_65017.append({
'2': 'arXiv',
'a': category,
})
self['65017'] = result_65017
self['035'] = result_035
return result_037
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 references2marc(self, key, value):
reference = value['reference']
pids = force_list(reference.get('persistent_identifiers'))
a_values = ['doi:' + el for el in force_list(reference.get('dois'))]
a_values.extend(
['hdl:' + el['value'] for el in pids if el.get('schema') == 'HDL'])
a_values.extend(
['urn:' + el['value'] for el in pids if el.get('schema') == 'URN'])
authors = force_list(reference.get('authors'))
e_values = [
el['full_name'] for el in authors if el.get('inspire_role') == 'editor'
]
h_values = [
el['full_name'] for el in authors if el.get('inspire_role') != 'editor'
]
r_values = force_list(reference.get('report_numbers'))
if reference.get('arxiv_eprint'):
arxiv_eprint = reference['arxiv_eprint']
r_values.append(
'arXiv:' +
arxiv_eprint if is_arxiv_post_2007(arxiv_eprint) else arxiv_eprint)
journal_title = get_value(reference, 'publication_info.journal_title')
journal_volume = get_value(reference, 'publication_info.journal_volume')
page_start = get_value(reference, 'publication_info.page_start')
page_end = get_value(reference, 'publication_info.page_end')
artid = get_value(reference, 'publication_info.artid')
s_value = build_pubnote(journal_title, journal_volume, page_start,
page_end, artid)
m_value = ' / '.join(force_list(reference.get('misc')))
return {
'0': get_recid_from_ref(value.get('record')),
'a': a_values,
'b': get_value(reference, 'publication_info.cnum'),
'c': reference.get('collaborations'),
'e': e_values,
'h': h_values,
'i': reference.get('isbn'),
'k': reference.get('texkey'),
'm': m_value,
'o': reference.get('label'),
'p': get_value(reference, 'imprint.publisher'),
'q': get_value(reference, 'publication_info.parent_title'),
'r': r_values,
's': s_value,
't': get_value(reference, 'title.title'),
'u': get_value(reference, 'urls.value'),
'x': get_value(value, 'raw_refs.value'),
'y': get_value(reference, 'publication_info.year'),
}
def arxiv_id(self, key, value):
if is_arxiv_post_2007(value):
arxiv_rep_number = {'value': 'arXiv:' + value}
else:
arxiv_rep_number = {'value': value}
if len(value.split('/')) == 2:
arxiv_rep_number['categories'] = value.split('/')[0]
if 'arxiv_eprints' in self:
self['arxiv_eprints'].append(arxiv_rep_number)
else:
self['arxiv_eprints'] = [arxiv_rep_number]
raise IgnoreKey
def arxiv_id(self, key, value):
if is_arxiv_post_2007(value):
arxiv_rep_number = {'value': 'arXiv:' + value}
else:
arxiv_rep_number = {'value': value}
if len(value.split('/')) == 2:
arxiv_rep_number['categories'] = value.split('/')[0]
if 'arxiv_eprints' in self:
self['arxiv_eprints'].append(arxiv_rep_number)
else:
self['arxiv_eprints'] = [arxiv_rep_number]
raise IgnoreKey
def _normalize_arxiv(obj):
"""Return a normalized arXiv identfier.
As in ``_is_arxiv``, we need to handle arXiv references as well
as arXiv identifiers. We also need to return a simpler arXiv
identifier than what ``idutils`` would output, so we use some
of its helpers instead of ``normalize_arxiv``.
"""
obj = obj.split()[0]
m = idutils.is_arxiv_pre_2007(obj)
if m:
return ''.join(m.group(2, 4, 5))
m = idutils.is_arxiv_post_2007(obj)
if m:
return '.'.join(m.group(2, 3))
def get_curation_body(template, metadata, email, extra_data):
"""
Get ticket content.
Ticket used by curators to curate the given record.
"""
from idutils import is_arxiv_post_2007
recid = extra_data.get('recid')
record_url = extra_data.get('url')
arxiv_id = metadata.get('arxiv_id')
if arxiv_id and is_arxiv_post_2007(arxiv_id):
arxiv_id = ''.join(['arXiv:', arxiv_id])
report_number = metadata.get('report_numbers')
if report_number:
report_number = report_number[0].get('value')
link_to_pdf = extra_data.get('submission_data').get('pdf')
subject = ' '.join(filter(lambda x: x is not None,
[arxiv_id,
" ".join(["doi:{0}".format(d) for d in metadata.get('dois')]),
report_number,
'(#{0})'.format(recid)]))
references = extra_data.get('submission_data').get('references')
user_comment = extra_data.get('submission_data').get('extra_comments')
body = render_template(
template,
recid=recid,
record_url=record_url,
link_to_pdf=link_to_pdf,
email=email,
references=references,
user_comment=user_comment,
).strip()
return subject, body
def get_curation_body(template, record, email, extra_data):
"""
Get ticket content.
Ticket used by curators to curate the given record.
"""
from idutils import is_arxiv_post_2007
recid = extra_data.get('recid')
record_url = extra_data.get('url')
arxiv_ids = record.get('arxiv_eprints.value')
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 = record.get('report_numbers.value')
dois = ["doi:{0}".format(record.get('dois.value'))]
link_to_pdf = 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 = extra_data.get('submission_data').get('references')
user_comment = extra_data.get('submission_data').get('extra_comments')
body = render_template(
template,
recid=recid,
record_url=record_url,
link_to_pdf=link_to_pdf,
email=email,
references=references,
user_comment=user_comment,
).strip()
return subject, body
def conflicts_ticket_context(user, obj):
server_name = current_app.config['SERVER_NAME']
workflow_id = obj.id
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 []
]
recid = obj.extra_data.get('recid')
subject = ' '.join(
filter(lambda x: x is not None,
arxiv_ids + dois + report_numbers + ['(#{0})'.format(recid)]))
return dict(server_name=server_name,
workflow_id=workflow_id,
arxiv_ids=arxiv_ids,
dois=dois,
recid=recid,
report_numbers=report_numbers,
subject=subject)
def get_primary_class(data, doc_type):
eprint = get_value(data, 'arxiv_eprints.value[0]')
if eprint and is_arxiv_post_2007(eprint):
return get_value(data, 'arxiv_eprints[0].categories[0]')
def references2marc(self, key, value):
"""Populate the ``999C5`` MARC field."""
reference = value.get('reference', {})
pids = force_list(reference.get('persistent_identifiers'))
a_values = ['doi:' + el for el in force_list(reference.get('dois'))]
a_values.extend(
['hdl:' + el['value'] for el in pids if el.get('schema') == 'HDL'])
a_values.extend(
['urn:' + el['value'] for el in pids if el.get('schema') == 'URN'])
external_ids = force_list(reference.get('external_system_identifiers'))
u_values = force_list(get_value(reference, 'urls.value'))
u_values.extend(
CDS_RECORD_FORMAT.format(el['value']) for el in external_ids
if el.get('schema') == 'CDS')
u_values.extend(
ADS_RECORD_FORMAT.format(el['value']) for el in external_ids
if el.get('schema') == 'ADS')
authors = force_list(reference.get('authors'))
e_values = [
el['full_name'] for el in authors if el.get('inspire_role') == 'editor'
]
h_values = [
el['full_name'] for el in authors if el.get('inspire_role') != 'editor'
]
r_values = force_list(reference.get('report_numbers'))
if reference.get('arxiv_eprint'):
arxiv_eprint = reference['arxiv_eprint']
r_values.append(
'arXiv:' +
arxiv_eprint if is_arxiv_post_2007(arxiv_eprint) else arxiv_eprint)
if reference.get('publication_info'):
reference['publication_info'] = convert_new_publication_info_to_old(
[reference['publication_info']])[0]
journal_title = get_value(reference, 'publication_info.journal_title')
journal_volume = get_value(reference, 'publication_info.journal_volume')
page_start = get_value(reference, 'publication_info.page_start')
page_end = get_value(reference, 'publication_info.page_end')
artid = get_value(reference, 'publication_info.artid')
s_value = build_pubnote(journal_title, journal_volume, page_start,
page_end, artid)
m_value = ' / '.join(force_list(reference.get('misc')))
return {
'0': get_recid_from_ref(value.get('record')),
'9': 'CURATOR' if value.get('legacy_curated') else None,
'a': a_values,
'b': get_value(reference, 'publication_info.cnum'),
'c': reference.get('collaborations'),
'e': e_values,
'h': h_values,
'i': reference.get('isbn'),
'k': reference.get('texkey'),
'm': m_value,
'o': reference.get('label'),
'p': get_value(reference, 'imprint.publisher'),
'q': get_value(reference, 'publication_info.parent_title'),
'r': r_values,
's': s_value,
't': get_value(reference, 'title.title'),
'u': u_values,
'x': get_value(value, 'raw_refs.value'),
'y': get_value(reference, 'publication_info.year'),
'z': 1 if value.get('curated_relation') else 0,
}
def get_primary_class(self, data):
eprint = get_value(data, "arxiv_eprints.value[0]")
if eprint and is_arxiv_post_2007(eprint):
return get_value(data, "arxiv_eprints[0].categories[0]")
def get_primary_class(data, doc_type):
eprint = get_value(data, 'arxiv_eprints.value[0]')
if eprint and is_arxiv_post_2007(eprint):
return get_value(data, 'arxiv_eprints[0].categories[0]')
