app/django/utils/stopwords.py
author Todd Larsen <tlarsen@google.com>
Mon, 27 Oct 2008 19:19:44 +0000
changeset 426 114fe0f840c8
parent 54 03e267d67478
permissions -rw-r--r--
Add tooltips style display of help_text, instead of widening the form with another (often ridiculously large) column. Also, version the .css and .js files so that browsers won't display the wrong cached one when we change something. Patch by: Dmitri Gaskin, Todd Larsen Review by: Todd Larsen

# 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)