How to use idutils - 10 common examples

def test_valid_doi(input_val, ctx):
    """Test DOI."""
    data, errors = MetadataSchemaV1(
        partial=['doi'], context=ctx).load(dict(doi=input_val))
    assert data['doi'] == idutils.normalize_doi(input_val.strip())

def test_identifier_schemes(app, db, minimal_record):
    """Test supported identifier schemes."""
    supported_schemes = [s for s, _ in idutils.PID_SCHEMES]
    minimal_record['related_identifiers'] = [
        {'scheme': scheme, 'relation': 'references', 'identifier': 'foobar'}
        for scheme in supported_schemes
    ]
    # JSONSchema validation should allow all supported schemes
    Record.create(minimal_record)

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 arxiv_id(self, key, value):
    from idutils import is_arxiv_post_2007

    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]

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 _is_arxiv(obj):
    """Return ``True`` if ``obj`` contains an arXiv identifier.

    The ``idutils`` library only handles arXiv identifiers, e.g. strings
    of the form ``arXiv:yymm.xxxxx``, but we sometimes have to deal with
    arXiv references, which might contain more information separated by
    a space. Therefore this helper wraps ``idutils`` to support this case.
    """
    arxiv_test = obj.split()
    if not arxiv_test:
        return False
    return idutils.is_arxiv(arxiv_test[0])

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 _serialize(self, value, attr, obj):
        if value is None:
            return None
        return idutils.to_url(value, 'doi', 'https')

def apply_rule(item, rule):
        r = copy.deepcopy(rule)
        r['link'] = idutils.to_url(item['identifier'], item['scheme'], 'https')
        return r

def _dump_common_links(self, obj):
        """Dump common links for deposits and records."""
        links = {}
        m = obj.get('metadata', {})

        doi = m.get('doi')
        if doi:
            links['badge'] = ui_link_for('badge', doi=quote(doi))
            links['doi'] = idutils.to_url(doi, 'doi', 'https')

        conceptdoi = m.get('conceptdoi')
        if conceptdoi:
            links['conceptbadge'] = ui_link_for('badge', doi=quote(conceptdoi))
            links['conceptdoi'] = idutils.to_url(conceptdoi, 'doi', 'https')

        files = m.get('_files', [])
        for f in files:
            if f.get('type') in thumbnail_exts:
                try:
                    # First previewable image is used for preview.
                    links['thumbs'] = self._thumbnail_urls(m.get('recid'))
                    links['thumb250'] = self._thumbnail_url(f, 250)
                except RuntimeError:
                    pass
                break