# stoplist - 
# loads a stop list of words into a dictionary, 
# creates a test dictionary with a random selection of the stoplist words,
# and then applies the stop list to the test dictionary,
# i.e. eliminates all the words in the stoplist from the test dictionary  

import string, random 

def load_stoplist(filename):
    infile = open(filename,'r')
    stoplist = {}
    for line in infile.readlines():
        word = string.strip(line)
        stoplist[word] = 1
    infile.close()
    return stoplist

def apply_stoplist(stoplist,dict):
    todelete = []
    for key in dict.keys():
        if stoplist.has_key(key):
           todelete.append(key)
    for key in todelete:
        del dict[key]

def make_random_selection(dict):
    keys = dict.keys()
    max = len(keys) - 1
    selections = []
    for i in range(1,100):
        selection = random.randrange(0,max,1)
        selections.append(keys[selection])
    return selections

def list_to_dict(list):
    dict = {}
    for item in list:
        dict[item] = 1
    return dict

filename = 'stoplist3.txt'
stoplist = load_stoplist(filename)
# print stoplist

words = make_random_selection(stoplist)
words_dict = list_to_dict(words)
print "words_dict: ", words_dict
apply_stoplist(stoplist,words_dict)
print "w/ stop words eliminated: ", words_dict

    Source: geocities.com/soho/square/3472

               ( geocities.com/soho/square)                   ( geocities.com/soho)