import sys
import summarisation
if len(sys.argv) < 2:
print "usage: python read.py filename"
quit()
filename = sys.argv[1]
sentences = summarisation.summarise(filename, debug_output=False)
print summarisation.outputspl(sentences)
# print sentences
"cd stanford-corenlp && java -cp stanford-corenlp-3.2.0.jar:stanford-corenlp-3.2.0-models.jar:xom.jar:joda-time.jar:jollyday.jar -Xmx3g edu.stanford.nlp.pipeline.StanfordCoreNLP -file "
+ filename)
sentences, coref = splitAndParse.splitSentencesAndParse("stanford-corenlp/" +
filename + ".xml")
order = range(len(sentences))
random.shuffle(order)
def cutoff_words(order, sentences, wc):
r = []
w = 0
for k in order:
sentence = sentences[k]
swc = summarisation.words(sentence)
if swc + w > wc:
r.append((k, summarisation.cut_words(sentence, wc - w)))
w = wc
else:
r.append((k, sentence))
w += swc
if w == wc:
break
r.sort()
return [rr[1] for rr in r]
print summarisation.outputspl(cutoff_words(order, sentences, 200))