def get(self):
# tokenList = word_tokenize("John's big idea isn't all that bad.")
# tokenList = pos_tag(word_tokenize("John's big idea isn't all that bad."))
stemmer = PorterStemmer()
plurals = ['caresses', 'flies', 'dies', 'mules', 'denied',
'died', 'agreed', 'owned', 'humbled', 'sized',
'meeting', 'stating', 'siezing', 'itemization',
'sensational', 'traditional', 'reference', 'colonizer',
'plotted']
singles = []
for plural in plurals:
singles.append(stemmer.stem(plural))
self.response.headers['Content-Type'] = 'text/html'
self.response.out.write('Hello test!')
self.response.out.write(singles)
nlProcessor = NLPlib()
s = "Very little is known about Beethoven's childhood. He was baptized on December 17, 1770 and was probably born a few days before that. [1][4][5][6] Beethoven's parents were Johann van Beethoven (1740 in Bonn - December 18, 1792) and Maria Magdalena Keverich (1744 in Ehrenbreitstein - July 17, 1787)."
v = nlProcessor.tokenize(s)
t = nlProcessor.tag(v)
for i in range(len(v)):
self.response.out.write(v[i] + "(" + t[i] + ")<br/>")
def test():
tweets = get_file_data(sys.argv[1])
posts = []
sys.path.append("/home/nsatvik/twitminer/miner")
print "1-Sports 2-Politics"
tagger = NLPlib()
for t in tweets:
posts.append(tweet(t, 1))
print posts[-1].get_text()
a = input("1 to display tags")
if a == 1:
words = tagger.tokenize(posts[-1].get_text())
tags = tagger.tag(words)
for i in range(len(words)):
print words[i], " ", tags[i]
else:
continue
def post(self):
nlProcessor = NLPlib()
content = self.request.get('content')
tokens = nlProcessor.tokenize(content)
taggedContent = nlProcessor.tag(tokens)
content = taggedContent
for i in range(len(taggedContent)):
isVerb = (taggedContent[i] == "VBD" or taggedContent[i] == "VBZ")
if isVerb:
correctVerb = tokens[i]
tokens[i] = "<select id=\"clozefox_answer\">"
tokens[i] += "<option value=\"wrongAnswer\">loves</option>"
tokens[i] += "<option value=\"wrongAnswer\">hates</option>"
tokens[i] += "<option value=\"trueAnswer\">" + correctVerb + "</option>"
tokens[i] += "</select>"
content = ' '.join(tokens)
self.response.headers['Content-Type'] = 'text/html'
self.response.out.write(content)
newlinearray = re.findall("[^\r\n]+?[\r\n]+?", line) #separate sentences in the tweet
#output_fpntr.write(str(newlinearray)+"\n")
tokens = [re.split("[ \t]+", line.strip()) for line in newlinearray] # separate every word using space as separator
# print tokens
# #extract words, punctiation and clitics
nopunctiation = []
for sentence in tokens:
newsentence = []
for word in sentence:
newtokens = re.compile("('(?:m|re|s|ll|ve|t)|n't|#\S+|\.[ \t]?\.(?:[ \t]*\.)*|-[ \t]*-(?:[ \t]*-)*|[!?\s]+|[^\w\s])", re.IGNORECASE).split(word)
noempty = [newtoken.strip() for newtoken in newtokens if newtoken.strip() != '']
newsentence = newsentence + noempty
if (newsentence != []): nopunctiation.append(newsentence)
sent = nopunctiation
tags = [tagger.tag(sent) for sent in nopunctiation ]
zipper = lambda x, y, z: [x[i]+y[i]+z[i] for i in range(0, len(x))]
zipped = [zipper(nopunctiation[i], ['/']*len(tags[i]), tags[i]) for i in range(0, len(tags))]
for sentence in zipped:
for i in range (0, len(sentence)):
output_fpntr.write(sentence[i])
if i != len(sentence) - 1: output_fpntr.write(' ')
output_fpntr.write('\n')
output_fpntr.write('|\n')
#output_fpntr.write('##########################################################\n')
#close file pointers
input_fpntr.close()
output_fpntr.close()
