def test_citekey_check_input_id_type():
with pytest.raises(TypeError) as excinfo:
CiteKey(None)
assert "input_id should be type 'str' not 'NoneType': None" == str(
excinfo.value)
with pytest.raises(TypeError):
CiteKey(0)
def standardize_id(self):
"""
Extract the standard_id (standard citation key) for a csl_item and modify the csl_item in-place to set its "id" field.
The standard_id is extracted from a "standard_citation" field, the "note" field, or the "id" field.
The extracted citation is checked for validity and standardized, after which it is the final "standard_id".
Regarding csl_item modification, the csl_item "id" field is set to the standard_citation and the note field
is created or updated with key-value pairs for standard_id and original_id.
Note that the Manubot software generally refers to the "id" of a CSL Item as a citekey.
However, in this context, we use "id" rather than "citekey" for consistency with CSL's "id" field.
"""
original_id = self.get("id")
self.infer_id()
original_standard_id = self["id"]
citekey = CiteKey(original_standard_id)
standard_id = citekey.standard_id
add_to_note = {}
note_dict = self.note_dict
if original_id and original_id != standard_id:
if original_id != note_dict.get("original_id"):
add_to_note["original_id"] = original_id
if original_standard_id and original_standard_id != standard_id:
if original_standard_id != note_dict.get("original_standard_id"):
add_to_note["original_standard_id"] = original_standard_id
if standard_id != note_dict.get("standard_id"):
add_to_note["standard_id"] = standard_id
self.note_append_dict(dictionary=add_to_note)
self.set_id(standard_id)
return self
def test_inspect_citekey_fails(citekey, contains):
"""
These citekeys should fail inspection by inspect_citekey.
"""
report = CiteKey(citekey).inspect()
assert report is not None
assert isinstance(report, str)
assert contains in report
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:
thumbnail_url = record.pop('thumbnail_url')
else:
thumbnail_url = get_thumbnail_url_from_html(html_url)
if thumbnail_url:
output['manubot']['thumbnail_url'] = thumbnail_url
for publication_type in 'preprint', 'journal':
citation = record.pop(f'{publication_type}_citation', None)
if not citation:
continue
citekey = CiteKey(citation)
if not citekey.is_handled_prefix:
logging.warning(f"unhandled citekey: {citation!r}")
continue
report = citekey.inspect()
if report:
logging.warning(
f"citekey failed inspection: {citation!r}\n{report}")
continue
output[publication_type] = {
'citation': citekey.standard_id,
}
for item in output.values():
csl_item = citekey_to_csl_item(item['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 __post_init__(self):
input_ids = list(dict.fromkeys(self.input_ids)) # deduplicate
self.citekeys = [CiteKey(x, self.aliases) for x in input_ids]
def test_citekey_check_input_id_at_prefix():
with pytest.raises(ValueError) as excinfo:
CiteKey("@my-citekey")
assert "input_id: '@my-citekey'\nstarts with '@'" in str(excinfo.value)
def test_citekey_class(input_id, citekey_attrs):
citekey = CiteKey(input_id)
print(citekey)
for key, value in citekey_attrs.items():
assert getattr(citekey, key) == value
assert citekey.short_id
def test_inspect_citekey_passes(citekey):
"""
These citekeys should pass inspection by inspect_citekey.
"""
report = CiteKey(citekey).inspect()
assert report is None
def test_citekey_standard_id(input_id, expected):
"""
Test CiteKey.standard_id property for common prefixes.
"""
citekey = CiteKey(input_id)
assert citekey.standard_id == expected