app/django/utils/stopwords.py
author Madhusudan C.S. <madhusudancs@gmail.com>
Sat, 06 Jun 2009 17:28:56 +0200
changeset 2401 bf70c5a0ef66
parent 54 03e267d67478
permissions -rw-r--r--
Added logic for every GHOP specific model. Defined logic for every model defined for GHOP. These logics do nothing special now. They are just inherited from their parent classes. Necessary GHOP specific logic will be added later as necessary. Reviewed by: Lennard de Rijk

# 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)