app/django/utils/stopwords.py
author Todd Larsen <tlarsen@google.com>
Mon, 11 Aug 2008 16:57:46 +0000
changeset 66 8c86470746fc
parent 54 03e267d67478
permissions -rw-r--r--
Finished migrating the "proto" app (which only contained a Person profile edit form) to the new combined trunk/app layout. Also, moved the form template from profile.html to profile/edit.html, to follow the "one template per view" approach (rather than have read-write vs. read-only logic in a single template).

# 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)