app/django/utils/stopwords.py
author Daniel Diniz <ajaksu@gmail.com>
Fri, 03 Jul 2009 14:35:03 +0200
changeset 2502 2e096acc8720
parent 54 03e267d67478
permissions -rw-r--r--
Surveys can now have required questions and comments can be turned on/off. Storing comments is now working. However some issues arise when form errors occur, like missing context and the errors also trigger before a form has been submitted. Reviewed by: Lennard de Rijk

# 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)