app/django/utils/stopwords.py
author Pawel Solyga <Pawel.Solyga@gmail.com>
Sun, 30 Nov 2008 16:44:27 +0000
changeset 627 88c486951f10
parent 54 03e267d67478
permissions -rw-r--r--
Remove python-graph from thirdparty, remove check_includes script and graph folder from scripts. This functionality is (cyclic imports check) is supported by pylint automatically so we don't need that any more. Patch by: Pawel Solyga Review by: Sverre Rabbelier

# 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)