def get_aliases_from_product_id_strings(product_id_strings):
aliases = []
logger.debug(u"in get_aliases_from_product_id_strings with product_id_strings {product_id_strings}".format(
product_id_strings=product_id_strings))
for nid in product_id_strings:
logger.debug(u"in get_aliases_from_product_id_strings nid 1 {nid}".format(
nid=nid))
nid = remove_nonprinting_characters(nid)
logger.debug(u"in get_aliases_from_product_id_strings nid 2 {nid}".format(
nid=nid))
nid = nid.strip() # also remove spaces
logger.debug(u"in get_aliases_from_product_id_strings with cleaned nid {nid}".format(
nid=nid))
if is_doi(nid):
aliases += crossref.Crossref().member_items(nid)
elif is_pmid(nid):
aliases += pubmed.Pubmed().member_items(nid)
elif is_arxiv(nid):
aliases += arxiv.Arxiv().member_items(nid)
elif is_url(nid):
aliases += webpage.Webpage().member_items(nid)
logger.debug(u"in get_aliases_from_product_id_strings with cleaned aliases {aliases}".format(
aliases=aliases))
return aliases
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(' "').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_pmid(input_pmid):
try:
pmid = remove_nonprinting_characters(input_pmid)
pmid = pmid.lower().replace("pmid:", "")
match = re.match("^(\d{3,15})$", pmid)
if match:
pmid = match.group(1)
else:
pmid = None
except AttributeError:
pmid = None
if not pmid:
logger.debug(u"MALFORMED PMID {input_pmid}".format(
input_pmid=input_pmid))
return pmid
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_url(input_url):
url = remove_nonprinting_characters(input_url)
return url
