so_far = (sortpl(so_far))[:k]
return so_far
# check while parsing the arguments that the number given is a nat.
def nat (string) :
value = int(string)
if value < 0:
msg = "%r is not a natural number" % string
raise argparse.ArgumentTypeError(msg)
return value
## describe and parse arguments from the command line
parser = argparse.ArgumentParser(description="Count the n most-used words in" +
"a corpus of English text.")
baseargs (parser)
parser.add_argument("-n" , "--number",
help="number of most frequently used words to compute. "
+ "defaults to 4.",
type=nat,
default=4)
args = parser.parse_args()
txtsrc = opentext (args.pdf , args.gutenberg , args.filename)
# traverse the whole file, adding canonical forms of valid words into a
# dictionary counting the number of appearances.
d = dict()
for line in txtsrc:
# get rid of ASCII em and en dashes
line = (line.replace("---", " ")).replace("--", " ")
print "looking for adjectives near nouns requires that you install nltk"
exit(1)
# check if a string is an English noun
def noun (string):
tag = nltk.pos_tag([string])
if not(tag[0][1] == 'NN' or tag[0][1] == 'NNP'):
msg = "%r is not a noun according to nltk" % string
raise argparse.ArgumentTypeError(msg)
return string
# describe and parse arguments from the command line
parser = argparse.ArgumentParser(description="Count the number of times a "
+ "noun appears after an adjective in a "
+ "corpus of English text.")
baseargs(parser, "nicer output if you have progressbar installed.")
parser.add_argument("noun", help="the noun for which to search", type=noun)
args = parser.parse_args()
txtsrc = opentext (args.pdf, args.gutenberg, args.filename)
# dump the corpus into a string so nltk can tokenize it
corpus = ""
for line in txtsrc:
corpus = corpus + (line.lower())
if not (args.pdf or args.gutenberg):
txtsrc.close()
if args.verbose:
print "read in text"
