def clean_doi(input_doi):
input_doi = remove_nonprinting_characters(input_doi)
try:
input_doi = input_doi.lower()
if input_doi.startswith("http"):
match = re.match("^https*://(dx\.)*doi.org/(10\..+)", input_doi)
doi = match.group(2)
elif "doi.org" in input_doi:
match = re.match("^(dx\.)*doi.org/(10\..+)", input_doi)
doi = match.group(2)
elif input_doi.startswith("doi:"):
match = re.match("^doi:(10\..+)", input_doi)
doi = match.group(1)
elif input_doi.startswith("10."):
doi = input_doi
elif "10." in input_doi:
match = re.match(".*(10\.\d+.+)", input_doi, re.DOTALL)
doi = match.group(1)
else:
doi = None
try:
logger.debug(
u"MALFORMED DOI {input_doi}".format(input_doi=input_doi))
except:
logger.debug(u"MALFORMED DOI, can't print doi")
except AttributeError:
doi = None
return doi
def clean_doi(input_doi):
input_doi = remove_nonprinting_characters(input_doi)
try:
input_doi = input_doi.lower()
if input_doi.startswith("http"):
match = re.match("^https*://(dx\.)*doi.org/(10\..+)", input_doi)
doi = match.group(2)
elif "doi.org" in input_doi:
match = re.match("^(dx\.)*doi.org/(10\..+)", input_doi)
doi = match.group(2)
elif input_doi.startswith("doi:"):
match = re.match("^doi:(10\..+)", input_doi)
doi = match.group(1)
elif input_doi.startswith("10."):
doi = input_doi
elif "10." in input_doi:
match = re.match(".*(10\.\d+.+)", input_doi, re.DOTALL)
doi = match.group(1)
else:
doi = None
try:
logger.debug(u"MALFORMED DOI {input_doi}".format(
input_doi=input_doi))
except:
logger.debug(u"MALFORMED DOI, can't print doi")
except AttributeError:
doi = None
return doi
def clean_id(nid):
try:
nid = nid.strip(' "')
nid = unicode_helpers.remove_nonprinting_characters(nid)
except (TypeError, AttributeError):
#isn't a string. That's ok, might be biblio
pass
return(nid)
def clean_id(nid):
try:
nid = nid.strip(' "')
nid = unicode_helpers.remove_nonprinting_characters(nid)
except (TypeError, AttributeError):
#isn't a string. That's ok, might be biblio
pass
return(nid)
def clean_doi(input_doi):
doi = None
input_doi = remove_nonprinting_characters(input_doi)
if input_doi.startswith("http"):
match = re.match("^https*://(dx\.)*doi.org/(10\..+)", input_doi)
doi = match.group(2)
elif input_doi.startswith("doi:"):
match = re.match("^doi:(10\..+)", input_doi)
doi = match.group(1)
elif input_doi.startswith("10."):
doi = input_doi
return doi
def clean_doi(input_doi):
doi = None
input_doi = remove_nonprinting_characters(input_doi)
if input_doi.startswith("http"):
match = re.match("^https*://(dx\.)*doi.org/(10\..+)", input_doi)
doi = match.group(2)
elif input_doi.startswith("doi:"):
match = re.match("^doi:(10\..+)", input_doi)
doi = match.group(1)
elif input_doi.startswith("10."):
doi = input_doi
return doi
def get_aliases_from_product_id_strings(product_id_strings):
aliases = []
for nid in product_id_strings:
nid = remove_nonprinting_characters(nid)
nid = nid.strip() # also remove spaces
if is_doi(nid):
aliases += providers.crossref.Crossref().member_items(nid)
elif is_pmid(nid):
aliases += providers.pubmed.Pubmed().member_items(nid)
elif is_arxiv(nid):
aliases += providers.arxiv.Arxiv().member_items(nid)
elif is_url(nid):
aliases += providers.webpage.Webpage().member_items(nid)
return aliases
def get_aliases_from_product_id_strings(product_id_strings):
aliases = []
for nid in product_id_strings:
nid = remove_nonprinting_characters(nid)
nid = nid.strip() # also remove spaces
if is_doi(nid):
aliases += providers.crossref.Crossref().member_items(nid)
elif is_pmid(nid):
aliases += providers.pubmed.Pubmed().member_items(nid)
elif is_arxiv(nid):
aliases += providers.arxiv.Arxiv().member_items(nid)
elif is_url(nid):
aliases += providers.webpage.Webpage().member_items(nid)
return aliases
def normalize_alias(alias):
(ns, nid) = alias
if ns == "biblio":
return (ns, nid)
nid = remove_nonprinting_characters(nid)
nid = nid.strip() # also remove spaces
if is_doi(nid):
nid = providers.crossref.clean_doi(nid)
elif is_pmid(nid):
nid = providers.pubmed.clean_pmid(nid)
elif is_arxiv(nid):
nid = providers.arxiv.clean_arxiv_id(nid)
elif is_url(nid):
nid = providers.webpage.clean_url(nid)
return (ns, nid)
def normalize_alias(alias):
(ns, nid) = alias
if ns == "biblio":
return (ns, nid)
nid = remove_nonprinting_characters(nid)
nid = nid.strip() # also remove spaces
if is_doi(nid):
nid = providers.crossref.clean_doi(nid)
elif is_pmid(nid):
nid = providers.pubmed.clean_pmid(nid)
elif is_arxiv(nid):
nid = providers.arxiv.clean_arxiv_id(nid)
elif is_url(nid):
nid = providers.webpage.clean_url(nid)
return (ns, nid)
def provider_memberitems_get(provider_name, query):
"""
Gets aliases associated with a query from a given provider.
"""
query = unicode_helpers.remove_nonprinting_characters(query)
provider = ProviderFactory.get_provider(provider_name)
try:
items_dict = provider.member_items(query)
except ProviderItemNotFoundError:
abort_custom(404, "item not found")
except (ProviderTimeout, ProviderServerError):
abort_custom(503, "crossref lookup error, might be transient")
except ProviderError:
abort(500, "internal error from provider")
resp = make_response(
json.dumps({"memberitems": items_dict}, sort_keys=True, indent=4), 200)
return resp
def provider_memberitems_get(provider_name, query):
"""
Gets aliases associated with a query from a given provider.
"""
query = unicode_helpers.remove_nonprinting_characters(query)
provider = ProviderFactory.get_provider(provider_name)
try:
items_dict = provider.member_items(query)
except ProviderItemNotFoundError:
abort_custom(404, "item not found")
except (ProviderTimeout, ProviderServerError):
abort_custom(503, "crossref lookup error, might be transient")
except ProviderError:
abort(500, "internal error from provider")
resp = make_response(
json.dumps({"memberitems": items_dict}, sort_keys=True, indent=4),
200
)
return resp
def test_remove_nonprinting_characters_unicode_input(self):
unicode_input = u'0000-0001-8907-4150\u200e' # a nonprinting character at the end
response = unicode_helpers.remove_nonprinting_characters(unicode_input)
expected = u"0000-0001-8907-4150"
assert_equals(response, expected)
def test_remove_nonprinting_characters(self):
unicode_input = u"hi"
response = unicode_helpers.remove_nonprinting_characters(unicode_input)
expected = u"hi"
assert_equals(response, expected)
def clean_pmid(pmid):
pmid = remove_nonprinting_characters(pmid)
pmid = pmid.lower().replace("pmid:", "")
return pmid
def clean_url(input_url):
url = remove_nonprinting_characters(input_url)
return url
def clean_url(input_url):
url = unicode_helpers.remove_nonprinting_characters(input_url)
return url
def test_remove_nonprinting_characters_unicode_input(self):
unicode_input = u'0000-0001-8907-4150\u200e' # a nonprinting character at the end
response = unicode_helpers.remove_nonprinting_characters(unicode_input)
expected = u"0000-0001-8907-4150"
assert_equals(response, expected)
def clean_url(input_url):
url = unicode_helpers.remove_nonprinting_characters(input_url)
return url
def clean_arxiv_id(arxiv_id):
arxiv_id = remove_nonprinting_characters(arxiv_id)
arxiv_id = arxiv_id.lower().replace("arxiv:",
"").replace("http://arxiv.org/abs/",
"")
return arxiv_id
def clean_arxiv_id(arxiv_id):
arxiv_id = remove_nonprinting_characters(arxiv_id)
arxiv_id = arxiv_id.lower().replace("arxiv:", "").replace("http://arxiv.org/abs/", "")
return arxiv_id
def test_remove_nonprinting_characters(self):
unicode_input = u"hi"
response = unicode_helpers.remove_nonprinting_characters(unicode_input)
expected = u"hi"
assert_equals(response, expected)
def clean_url(input_url):
url = remove_nonprinting_characters(input_url)
return url
