def _strip_scales(self, text):
# '1:100:000'
scale_pttn = ur"(1:[\d]{0,}(,[\d]{3}){1,})"
m = match(text, scale_pttn)
if m:
return ''
return text
def _verify_urn(self, potential_urn):
# not much point to this but we're just going to leave it
pttn = re.compile(
ur'^([a-z0-9.#]{0,}:([a-z0-9][a-z0-9.-]{0,31}):[a-z0-9A-Z_()+,-.:=@;$!*\'%/?#\[\]]+)',
re.IGNORECASE
)
m = match(potential_urn, pttn)
return potential_urn if m else ''
def _verify_url(self, potential_url):
# ugh
if 'mailto:' in potential_url:
return ''
# is it a urn?
pttn = re.compile(
ur'^([a-z0-9]{0,}:[a-z0-9][a-z0-9-]{0,31}:[a-z0-9()+,\-.:=@;$_!*\'%/?#\[\]]+)',
re.IGNORECASE
)
urn_m = match(potential_url, pttn)
if urn_m:
return ''
# does it even have a scheme?
try:
u = uparse(potential_url, rule='URI')
if not u.get('scheme'):
# will consider the leading blob of a URN
# a scheme even if we don't so this is not
# 100% reliable
return ''
parts = potential_url.split(':', 1)
if not parts[1].startswith('/') or len(parts) < 2:
# so if it's our false urn scheme, we
# say it has to be :// or it's not a url
# and it has to have a split
return ''
except:
return ''
pttn = re.compile(ur"""(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)\b/?(?!@)))""", re.IGNORECASE)
m = match(potential_url, pttn)
if not m:
return ''
return potential_url
def _extract_identifiers(self, text):
# make sure it's not a date first
text = self._strip_dates(text)
if not text:
yield '', ''
for pattern_type, pattern in _pattern_set:
m = match(text, pattern)
if not m:
continue
# if the pattern type doesn't match the
# verification ie urn is not actually urn
# bounce (this is mostly for urls)
urn_verified = self._verify_urn(m)
is_urn = urn_verified != ''
if urn_verified:
yield 'urn', m
if pattern_type == 'urn' and not is_urn:
continue
# NOTE: this should be a bit of dead twig code
url_verified = self._verify_url(m)
is_url = url_verified.strip() != ''
if is_url and not is_urn:
if 'dx.doi.org' in m:
t = 'doi'
elif 'hdl.handle.net' in m:
t = 'hdl'
else:
t = 'url'
yield t, m
if pattern_type == 'url' and not is_url:
continue
m = self._tidy_text(m)
if not m:
continue
yield pattern_type, m