def formdata_to_model(obj, formdata):
"""Manipulate form data to match literature data model."""
def _is_arxiv_url(url):
return 'arxiv.org' in url
form_fields = copy.deepcopy(formdata)
filter_empty_elements(
form_fields, ['authors', 'supervisors', 'report_numbers']
)
builder = LiteratureBuilder(source='submitter')
for author in form_fields.get('authors', []):
builder.add_author(builder.make_author(
author['full_name'],
affiliations=force_list(author['affiliation'])
if author['affiliation'] else None,
roles=['author']
))
for supervisor in form_fields.get('supervisors', []):
builder.add_author(builder.make_author(
supervisor['full_name'],
affiliations=force_list(supervisor['affiliation'])
if author['affiliation'] else None,
roles=['supervisor']
))
builder.add_title(title=form_fields.get('title'))
document_type = 'conference paper' if form_fields.get('conf_name') \
else form_fields.get('type_of_doc', [])
builder.add_document_type(
document_type=document_type
)
builder.add_abstract(
abstract=form_fields.get('abstract'),
source='arXiv' if form_fields.get('categories') else None
)
if form_fields.get('arxiv_id') and form_fields.get('categories'):
builder.add_arxiv_eprint(
arxiv_id=form_fields.get('arxiv_id'),
arxiv_categories=form_fields.get('categories').split()
)
builder.add_doi(doi=form_fields.get('doi'))
builder.add_inspire_categories(
subject_terms=form_fields.get('subject_term'),
source='user'
)
for key in ('extra_comments', 'nonpublic_note',
'hidden_notes', 'conf_name', 'references'):
builder.add_private_note(
private_notes=form_fields.get(key)
)
year = form_fields.get('year')
try:
year = int(year)
except (TypeError, ValueError):
year = None
builder.add_publication_info(
year=year,
cnum=form_fields.get('conference_id'),
journal_issue=form_fields.get('issue'),
journal_title=form_fields.get('journal_title'),
journal_volume=form_fields.get('volume'),
page_start=form_fields.get('page_start'),
page_end=form_fields.get('page_end'),
artid=form_fields.get('artid')
)
builder.add_preprint_date(
preprint_date=form_fields.get('preprint_created')
)
if form_fields.get('type_of_doc') == 'thesis':
builder.add_thesis(
defense_date=form_fields.get('defense_date'),
degree_type=form_fields.get('degree_type'),
institution=form_fields.get('institution'),
date=form_fields.get('thesis_date')
)
builder.add_accelerator_experiments_legacy_name(
legacy_name=form_fields.get('experiment')
)
language = form_fields.get('other_language') \
if form_fields.get('language') == 'oth' \
else form_fields.get('language')
builder.add_language(language=language)
builder.add_title_translation(title=form_fields.get('title_translation'))
builder.add_title(
title=form_fields.get('title_arXiv'),
source='arXiv'
)
builder.add_title(
title=form_fields.get('title_crossref'),
source='crossref'
)
builder.add_license(url=form_fields.get('license_url'))
builder.add_public_note(public_note=form_fields.get('public_notes'))
builder.add_public_note(
public_note=form_fields.get('note'),
source='arXiv' if form_fields.get('categories') else 'CrossRef'
)
form_url = form_fields.get('url')
form_additional_url = form_fields.get('additional_url')
if form_url and not _is_arxiv_url(form_url):
obj.extra_data['submission_pdf'] = form_url
if not form_additional_url:
builder.add_url(url=form_url)
if form_additional_url and not _is_arxiv_url(form_additional_url):
builder.add_url(url=form_additional_url)
[builder.add_report_number(
report_number=report_number.get('report_number')
) for report_number in form_fields.get('report_numbers', [])]
builder.add_collaboration(collaboration=form_fields.get('collaboration'))
builder.add_acquisition_source(
datetime=datetime.datetime.utcnow().isoformat(),
submission_number=obj.id,
internal_uid=int(obj.id_user),
email=form_fields.get('email'),
orcid=form_fields.get('orcid'),
method='submitter'
)
builder.validate_record()
return builder.record
def formdata_to_model(obj, formdata):
"""Manipulate form data to match literature data model."""
def _is_arxiv_url(url):
return 'arxiv.org' in url
form_fields = copy.deepcopy(formdata)
filter_empty_elements(form_fields,
['authors', 'supervisors', 'report_numbers'])
builder = LiteratureBuilder(source='submitter')
for author in form_fields.get('authors', []):
builder.add_author(
builder.make_author(author['full_name'],
affiliations=force_list(author['affiliation'])
if author['affiliation'] else None,
roles=['author']))
for supervisor in form_fields.get('supervisors', []):
builder.add_author(
builder.make_author(
supervisor['full_name'],
affiliations=force_list(supervisor['affiliation'])
if author['affiliation'] else None,
roles=['supervisor']))
builder.add_title(title=form_fields.get('title'))
document_type = 'conference paper' if form_fields.get('conf_name') \
else form_fields.get('type_of_doc', [])
if document_type == 'chapter':
document_type = 'book chapter'
builder.add_document_type(document_type=document_type)
builder.add_abstract(
abstract=form_fields.get('abstract'),
source='arXiv' if form_fields.get('categories') else None)
if form_fields.get('arxiv_id') and form_fields.get('categories'):
builder.add_arxiv_eprint(
arxiv_id=form_fields.get('arxiv_id'),
arxiv_categories=form_fields.get('categories').split())
builder.add_doi(doi=form_fields.get('doi'))
builder.add_inspire_categories(
subject_terms=form_fields.get('subject_term'), source='user')
for key in ('extra_comments', 'nonpublic_note', 'hidden_notes',
'conf_name'):
builder.add_private_note(private_notes=form_fields.get(key))
year = form_fields.get('year')
try:
year = int(year)
except (TypeError, ValueError):
year = None
builder.add_preprint_date(
preprint_date=form_fields.get('preprint_created'))
if form_fields.get('type_of_doc') == 'thesis':
builder.add_thesis(defense_date=form_fields.get('defense_date'),
degree_type=form_fields.get('degree_type'),
institution=form_fields.get('institution'),
date=form_fields.get('thesis_date'))
if form_fields.get('type_of_doc') == 'chapter':
if not form_fields.get('journal_title'):
builder.add_book_series(title=form_fields.get('series_title'))
if form_fields.get('type_of_doc') == 'book':
if form_fields.get('journal_title'):
form_fields['volume'] = form_fields.get('series_volume')
else:
builder.add_book_series(title=form_fields.get('series_title'),
volume=form_fields.get('series_volume'))
builder.add_book(publisher=form_fields.get('publisher_name'),
place=form_fields.get('publication_place'),
date=form_fields.get('publication_date'))
builder.add_publication_info(
year=year,
cnum=form_fields.get('conference_id'),
journal_issue=form_fields.get('issue'),
journal_title=form_fields.get('journal_title'),
journal_volume=form_fields.get('volume'),
page_start=form_fields.get('start_page'),
page_end=form_fields.get('end_page'),
artid=form_fields.get('artid'),
parent_record=form_fields.get('parent_book'))
builder.add_accelerator_experiments_legacy_name(
legacy_name=form_fields.get('experiment'))
language = form_fields.get('other_language') \
if form_fields.get('language') == 'oth' \
else form_fields.get('language')
builder.add_language(language=language)
if form_fields.get('title_translation'):
builder.add_title_translation(
title=form_fields['title_translation'],
language='en',
)
builder.add_title(title=form_fields.get('title_arXiv'), source='arXiv')
builder.add_title(title=form_fields.get('title_crossref'),
source='crossref')
builder.add_license(url=form_fields.get('license_url'))
builder.add_public_note(public_note=form_fields.get('public_notes'))
builder.add_public_note(
public_note=form_fields.get('note'),
source='arXiv' if form_fields.get('categories') else 'CrossRef')
form_url = form_fields.get('url')
form_additional_url = form_fields.get('additional_url')
if form_url and not _is_arxiv_url(form_url):
obj.extra_data['submission_pdf'] = form_url
if not form_additional_url:
builder.add_url(url=form_url)
if form_additional_url and not _is_arxiv_url(form_additional_url):
builder.add_url(url=form_additional_url)
[
builder.add_report_number(
report_number=report_number.get('report_number'))
for report_number in form_fields.get('report_numbers', [])
]
builder.add_collaboration(collaboration=form_fields.get('collaboration'))
builder.add_acquisition_source(
datetime=datetime.datetime.utcnow().isoformat(),
submission_number=obj.id,
internal_uid=int(obj.id_user),
email=form_fields.get('email'),
orcid=form_fields.get('orcid'),
method='submitter')
return builder.record
def hepcrawl_to_hep(crawler_record):
"""
Args:
crawler_record(dict): dictionary representing the hepcrawl formatted
record.
Returns:
dict: The hep formatted record.
"""
def _filter_affiliation(affiliations):
return [
affilation.get('value')
for affilation in affiliations
if affilation.get('value')
]
builder = LiteratureBuilder(
source=crawler_record['acquisition_source']['source']
)
for author in crawler_record.get('authors', []):
builder.add_author(builder.make_author(
full_name=author['full_name'],
raw_affiliations=_filter_affiliation(author['affiliations']),
))
for title in crawler_record.get('titles', []):
builder.add_title(
title=title.get('title'),
subtitle=title.get('subtitle'),
source=title.get('source')
)
for abstract in crawler_record.get('abstracts', []):
builder.add_abstract(
abstract=abstract.get('value'),
source=abstract.get('source')
)
for arxiv_eprint in crawler_record.get('arxiv_eprints', []):
builder.add_arxiv_eprint(
arxiv_id=arxiv_eprint.get('value'),
arxiv_categories=arxiv_eprint.get('categories')
)
for doi in crawler_record.get('dois', []):
builder.add_doi(
doi=doi.get('value'),
material=doi.get('material'),
)
for private_note in crawler_record.get('private_notes', []):
builder.add_private_note(
private_notes=private_note
)
for public_note in crawler_record.get('public_notes', []):
builder.add_public_note(
public_note=public_note.get('value'),
source=public_note.get('source')
)
for license in crawler_record.get('license', []):
builder.add_license(
url=license.get('url'),
license=license.get('license'),
material=license.get('material'),
)
for collaboration in crawler_record.get('collaborations', []):
builder.add_collaboration(
collaboration=collaboration.get('value')
)
for imprint in crawler_record.get('imprints', []):
builder.add_imprint_date(
imprint_date=imprint.get('date')
)
for copyright in crawler_record.get('copyright', []):
builder.add_copyright(
holder=copyright.get('holder'),
material=copyright.get('material'),
statement=copyright.get('statement')
)
builder.add_preprint_date(
preprint_date=crawler_record.get('preprint_date')
)
acquisition_source = crawler_record.get('acquisition_source', {})
builder.add_acquisition_source(
method=acquisition_source['method'],
date=acquisition_source['datetime'],
source=acquisition_source['source'],
submission_number=acquisition_source['submission_number'],
)
try:
builder.add_number_of_pages(
number_of_pages=int(crawler_record.get('page_nr', [])[0])
)
except (TypeError, ValueError, IndexError):
pass
publication_types = [
'introductory',
'lectures',
'review',
'manual',
]
document_types = [
'book',
'note',
'report',
'proceedings',
'thesis',
]
added_doc_type = False
for collection in crawler_record.get('collections', []):
collection = collection['primary'].strip().lower()
if collection == 'arxiv':
continue # ignored
elif collection == 'citeable':
builder.set_citeable(True)
elif collection == 'core':
builder.set_core(True)
elif collection == 'noncore':
builder.set_core(False)
elif collection == 'published':
builder.set_refereed(True)
elif collection == 'withdrawn':
builder.set_withdrawn(True)
elif collection in publication_types:
builder.add_publication_type(collection)
elif collection == 'bookchapter':
added_doc_type = True
builder.add_document_type('book chapter')
elif collection == 'conferencepaper':
added_doc_type = True
builder.add_document_type('conference paper')
elif collection in document_types:
added_doc_type = True
builder.add_document_type(collection)
if not added_doc_type:
builder.add_document_type('article')
_pub_info = crawler_record.get('publication_info', [{}])[0]
builder.add_publication_info(
year=_pub_info.get('year'),
artid=_pub_info.get('artid'),
page_end=_pub_info.get('page_end'),
page_start=_pub_info.get('page_start'),
journal_issue=_pub_info.get('journal_issue'),
journal_title=_pub_info.get('journal_title'),
journal_volume=_pub_info.get('journal_volume'),
pubinfo_freetext=_pub_info.get('pubinfo_freetext'),
material=_pub_info.get('pubinfo_material'),
)
for report_number in crawler_record.get('report_numbers', []):
builder.add_report_number(
report_number=report_number.get('value'),
source=report_number.get('source')
)
for url in crawler_record.get('urls', []):
builder.add_url(url=url.get('value'))
for document in crawler_record.get('documents', []):
builder.add_document(
description=document.get('description'),
fulltext=document.get('fulltext'),
hidden=document.get('hidden'),
key=document['key'],
material=document.get('material'),
original_url=document.get('original_url'),
url=document['url'],
)
return builder.record
