def test_citation_to_citeproc_pubmed_book():
"""
Extracting CSL metadata from books in PubMed is not supported.
Logic not implemented to parse XML returned by
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=29227604&rettype=full
"""
with pytest.raises(NotImplementedError):
citation_to_citeproc('pmid:29227604')
def process_record(record):
"""
Expand a catalog record with retrieved metadata
"""
output = {}
html_url = record.pop('html_url')
output['manubot'] = {
'repo_url': record.pop('repo_url'),
'url': html_url,
'citation': f"url:{html_url}",
}
if 'thumbnail_url' in record:
output['manubot']['thumbnail_url'] = record.pop('thumbnail_url')
for publication_type in 'preprint', 'journal':
citation = record.pop(f'{publication_type}_citation', None)
if not citation:
continue
if not is_valid_citation(citation):
continue
output[publication_type] = {
'citation': citation,
}
for item in output.values():
citation = standardize_citation(item['citation'])
csl_item = citation_to_citeproc(citation)
if 'url' not in item and 'URL' in csl_item:
item['url'] = csl_item['URL']
item['title'] = get_title(csl_item)
item['authors'] = get_authors_text(csl_item)
item['journal'] = get_journal(csl_item)
item['date_iso'] = get_date(csl_item)
item['date_human'] = get_date_summary(csl_item)
item['csl_item'] = csl_item
output['extras'] = record
return output
def test_citation_to_citeproc_pubmed_with_numeric_month():
"""
Generated from XML returned by
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=29028984&rettype=full
See https://github.com/manubot/manubot/issues/69
"""
citation = 'pmid:29028984'
citeproc = citation_to_citeproc(citation)
print(citeproc)
assert citeproc['issued']['date-parts'] == [[2018, 3, 15]]
def test_citation_to_citeproc_doi_datacite():
citation = 'doi:10.7287/peerj.preprints.3100v1'
citeproc = citation_to_citeproc(citation)
assert citeproc['id'] == '11cb5HXoY'
assert citeproc['URL'] == 'https://doi.org/10.7287/peerj.preprints.3100v1'
assert citeproc['DOI'] == '10.7287/peerj.preprints.3100v1'
assert citeproc['type'] == 'report'
assert citeproc['title'] == 'Sci-Hub provides access to nearly all scholarly literature'
authors = citeproc['author']
assert authors[0]['family'] == 'Himmelstein'
assert authors[-1]['family'] == 'Greene'
def test_citation_to_citeproc_arxiv():
citation = 'arxiv:cond-mat/0703470v2'
citeproc = citation_to_citeproc(citation)
assert citeproc['id'] == 'ES92tcdg'
assert citeproc['URL'] == 'https://arxiv.org/abs/cond-mat/0703470v2'
assert citeproc['number'] == 'cond-mat/0703470v2'
assert citeproc['version'] == '2'
assert citeproc['type'] == 'report'
assert citeproc['container-title'] == 'arXiv'
assert citeproc['title'] == 'Portraits of Complex Networks'
authors = citeproc['author']
assert authors[0]['literal'] == 'J. P. Bagrow'
assert citeproc['DOI'] == '10.1209/0295-5075/81/68004'
def generate_csl_items(args, citation_df):
"""
General CSL (citeproc) items for standard_ids in citation_df.
Writes references.json to disk and logs warnings for potential problems.
"""
# Read manual references (overrides) in JSON CSL
manual_refs = load_manual_references(args.manual_references_paths)
requests_cache.install_cache(args.requests_cache_path,
include_get_headers=True)
cache = requests_cache.get_cache()
if args.clear_requests_cache:
logging.info('Clearing requests-cache')
requests_cache.clear()
logging.info(
f'requests-cache starting with {len(cache.responses)} cached responses'
)
csl_items = list()
failures = list()
for standard_id in citation_df.standard_id.unique():
if standard_id in manual_refs:
csl_items.append(manual_refs[standard_id])
continue
elif standard_id.startswith('raw:'):
logging.error(
f'CSL JSON Data with a standard_id of {standard_id} not found in manual-references.json. '
'Metadata must be provided for raw citations.')
failures.append(standard_id)
try:
citeproc = citation_to_citeproc(standard_id)
csl_items.append(citeproc)
except Exception:
logging.exception(f'Citeproc retrieval failure for {standard_id}')
failures.append(standard_id)
logging.info(
f'requests-cache finished with {len(cache.responses)} cached responses'
)
requests_cache.uninstall_cache()
if failures:
message = 'CSL JSON Data retrieval failed for:\n{}'.format(
'\n'.join(failures))
logging.error(message)
# Write JSON CSL bibliography for Pandoc.
with args.references_path.open('w') as write_file:
json.dump(csl_items, write_file, indent=2, ensure_ascii=False)
write_file.write('\n')
return csl_items
def test_citation_to_citeproc_pmc(identifier, citation_id):
citation = f'pmcid:{identifier}'
citeproc = citation_to_citeproc(citation)
assert citeproc['id'] == citation_id
assert citeproc[
'URL'] == 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041534/'
assert citeproc[
'container-title'] == 'Summit on Translational Bioinformatics'
assert citeproc[
'title'] == 'Secondary Use of EHR: Data Quality Issues and Informatics Opportunities'
authors = citeproc['author']
assert authors[0]['family'] == 'Botsis'
assert citeproc['PMID'] == '21347133'
assert citeproc['PMCID'] == 'PMC3041534'
def test_citation_to_citeproc_pmc():
"""
https://api.ncbi.nlm.nih.gov/lit/ctxp/v1/pmc/?format=csl&id=3041534
"""
citation = f'pmcid:PMC3041534'
citeproc = citation_to_citeproc(citation)
assert citeproc['id'] == 'RoOhUFKU'
assert citeproc['URL'] == 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041534/'
assert citeproc['container-title-short'] == 'Summit Transl Bioinform'
assert citeproc['title'] == 'Secondary Use of EHR: Data Quality Issues and Informatics Opportunities'
authors = citeproc['author']
assert authors[0]['family'] == 'Botsis'
assert citeproc['PMID'] == '21347133'
assert citeproc['PMCID'] == 'PMC3041534'
assert 'generated by Manubot' in citeproc['note']
assert 'standard_id: pmcid:PMC3041534' in citeproc['note']
def test_citation_to_citeproc_pubmed_1():
"""
Generated from XML returned by
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=21347133&rettype=full
"""
citation = 'pmid:21347133'
citeproc = citation_to_citeproc(citation)
assert citeproc['id'] == 'y9ONtSZ9'
assert citeproc['type'] == 'article-journal'
assert citeproc['URL'] == 'https://www.ncbi.nlm.nih.gov/pubmed/21347133'
assert citeproc['container-title'] == 'Summit on translational bioinformatics'
assert citeproc['title'] == 'Secondary Use of EHR: Data Quality Issues and Informatics Opportunities.'
assert citeproc['issued']['date-parts'] == [[2010, 3, 1]]
authors = citeproc['author']
assert authors[0]['given'] == 'Taxiarchis'
assert authors[0]['family'] == 'Botsis'
assert citeproc['PMID'] == '21347133'
assert citeproc['PMCID'] == 'PMC3041534'
def test_citation_to_citeproc_pubmed_2():
"""
Generated from XML returned by
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=27094199&rettype=full
"""
citation = 'pmid:27094199'
citeproc = citation_to_citeproc(citation)
print(citeproc)
assert citeproc['id'] == 'alaFV9OY'
assert citeproc['type'] == 'article-journal'
assert citeproc['URL'] == 'https://www.ncbi.nlm.nih.gov/pubmed/27094199'
assert citeproc['container-title'] == 'Circulation. Cardiovascular genetics'
assert citeproc['container-title-short'] == 'Circ Cardiovasc Genet'
assert citeproc['page'] == '179-84'
assert citeproc['title'] == 'Genetic Association-Guided Analysis of Gene Networks for the Study of Complex Traits.'
assert citeproc['issued']['date-parts'] == [[2016, 4]]
authors = citeproc['author']
assert authors[0]['given'] == 'Casey S'
assert authors[0]['family'] == 'Greene'
assert citeproc['PMID'] == '27094199'
assert citeproc['DOI'] == '10.1161/circgenetics.115.001181'
def test_citation_to_citeproc_isbn():
csl_item = citation_to_citeproc('isbn:9780387950693')
assert csl_item['type'] == 'book'
assert csl_item['title'] == 'Complex analysis'
