app/django/utils/stopwords.py
author Sverre Rabbelier <srabbelier@gmail.com>
Sat, 28 Mar 2009 20:19:50 +0000
changeset 2026 388b65cabfbb
parent 54 03e267d67478
permissions -rw-r--r--
Set fields to 100% width again This patch properly fixes the problem without punishing other browsers for IE's brokenness. If we have any other IE specific fixes, we should include them in this way too. Patch by: Timothy Robert Ansell <tansell@google.com>

# 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)