app/django/utils/stopwords.py
author Lennard de Rijk <ljvderijk@gmail.com>
Fri, 23 Jan 2009 12:00:48 +0000
changeset 920 39badbfb80be
parent 54 03e267d67478
permissions -rw-r--r--
Added the new way to process invites for club_admin only. This patch contains the separability needed to ensure that we can successfully do the access checks we need. Host invites can for the time being only be completed by developers due to the reorganization. Patch by: Lennard de Rijk 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)