app/django/utils/stopwords.py
author Sverre Rabbelier <srabbelier@gmail.com>
Wed, 03 Dec 2008 23:49:10 +0000
changeset 662 0e89b027b140
parent 54 03e267d67478
permissions -rw-r--r--
Make use of the new generic key_name by lookup up scope_path This way base classes do not have to look up the 'scope' property, instead they can rely on the base class to do it for them provided they define the 'scope_logic' param. Patch 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)