app/django/utils/stopwords.py
author Todd Larsen <tlarsen@google.com>
Fri, 21 Nov 2008 08:13:52 +0000
changeset 531 b74bf6bf1ccf
parent 54 03e267d67478
permissions -rw-r--r--
Make editSelf() work by adding 'inheritance_line' to the list of excluded fields in the UserForm. Also, fix a few too-long lines and add some missing parentheses (the style guide says do not rely on operator precedence). Patch 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)