How to use manubot - 10 common examples

https://stackoverflow.com/a/16493707/4651668
    Command modeled after:
    git --work-tree=webpage checkout upstream/gh-pages -- v
    """
    if not args.checkout:
        return
    command = [
        "git",
        f"--work-tree={args.webpage_directory}",
        "checkout",
        args.checkout,
        "--",
        "v",
    ]
    logging.info(
        f"Attempting checkout with the following command:\n{shlex_join(command)}"
    )
    process = subprocess.run(command, stderr=subprocess.PIPE)
    if process.returncode == 0:
        # Addresses an odd behavior where git checkout stages v/* files that don't actually exist
        subprocess.run(["git", "add", "v"])
    else:
        stderr = process.stderr.decode()
        message = (
            f"Checkout returned a nonzero exit status. See stderr:\n{stderr.rstrip()}"
        )
        if "pathspec" in stderr:
            message += (
                "\nManubot note: if there are no preexisting webpage versions (like for a newly created manuscript), "
                "the pathspec error above is expected and can be safely ignored."
            )  # see https://github.com/manubot/rootstock/issues/183
        logging.warning(message)

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'] == 'AMIA Jt Summits Transl Sci Proc'
    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_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'

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 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 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/greenelab/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_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'] == 'AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science'
    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_version():
    stdout = subprocess.check_output(
        ['manubot', '--version'],
        universal_newlines=True,
    )
    version_str = f'v{manubot.__version__}'
    assert version_str == stdout.rstrip()