app/django/utils/stopwords.py
author Todd Larsen <tlarsen@google.com>
Wed, 15 Oct 2008 17:10:27 +0000
changeset 339 b9be44e09530
parent 54 03e267d67478
permissions -rw-r--r--
Define the Models for implementing Quizzes (collections of Questions) and their Responses (collections of Answers to those Questions). These Models would form the basis of storage for such items as: Terms of Service (Quiz) Question ("I agree...") Response -> Answer (answer to "I agree..." confirmation) solution ("Yes" Answer to the "I agree..." Question) Mentor and Student surveys (Quiz) Questions (including "Pay this student?") Response -> Answers solution ("Yes" Answer to the "Pay this student?" Question) Organization applications Student Proposal review, comment, and scoring system GHOP task tracking (a specific task list item would be a Quiz) Patch by: Todd Larsen Review by: Pawel Solyga, Sverre Rabbelier, Chen Lunpeng Review URL: http://codereviews.googleopensourceprograms.com/1403

# 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)