app/django/utils/stopwords.py
author Pawel Solyga <Pawel.Solyga@gmail.com>
Fri, 17 Oct 2008 13:57:54 +0000
changeset 369 2955eff2bf94
parent 54 03e267d67478
permissions -rw-r--r--
Replace GROUP_TYPE_PLURAL and GROUP_TYPE_SHORT constants in Group models with more generic TYPE_NAME, TYPE_NAME_SHORT, TYPE_NAME_PLURAL names and apply changes in affected files. Use ugettext_lazy for TYPE_NAME and TYPE_NAME_PLURAL constants. This approach is similar to the upcoming refactor of views. Patch by: Pawel Solyga Review 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)