Move LINK_ID and SCOPE_PATH regular expressions to soc/models/linkable.py.
Fix some too-long lines. Change key names back to type:scope_path/link_id
(instead of type:scope_path:link_id). Some minor __doc__ string updates.
Patch by: Todd Larsen
# Performance note: I benchmarked this code using a set instead of
# a list for the stopwords and was surprised to find that the list
# performed /better/ than the set - maybe because it's only a small
# list.
stopwords = '''
i
a
an
are
as
at
be
by
for
from
how
in
is
it
of
on
or
that
the
this
to
was
what
when
where
'''.split()
def strip_stopwords(sentence):
"Removes stopwords - also normalizes whitespace"
words = sentence.split()
sentence = []
for word in words:
if word.lower() not in stopwords:
sentence.append(word)
return u' '.join(sentence)