app/django/utils/stopwords.py
author Sverre Rabbelier <srabbelier@gmail.com>
Thu, 16 Oct 2008 23:23:16 +0000
changeset 363 d35ffa6ca643
parent 54 03e267d67478
permissions -rw-r--r--
Add a framework for generic views This commit does not enable the new code, as such there should be no change in functionality. In order to use the new code the maps.py file should be updated to point at the new views/models/sponsor.py module. Patch by: Sverre Rabbelier Reviewed by: to-be-reviewed

# 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)