app/django/utils/stopwords.py
author Sverre Rabbelier <srabbelier@gmail.com>
Sun, 16 Nov 2008 17:59:30 +0000
changeset 490 7cfa2ad62944
parent 54 03e267d67478
permissions -rw-r--r--
Allow pre-seeding a create form With this feature the Site Settings create form can be pre-seeded with it's "magic values", which allows those fields to be hidden from the user. At the same time, it allows 'Edit Main Site Settings' to either create or edit the Main Site Settings.

# 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)