haikus.py

from curses.ascii import isdigit 
from nltk.corpus import cmudict 
import numpy as np
from  string import punctuation
from nltk.tokenize import sent_tokenize


d = cmudict.dict() 

def nsyl(word): 
    try:
        return [len(list(y for y in x if isdigit(y[-1]))) for x in d[word.strip(punctuation).lower()]] 
    except Exception, e:
        return [99]

def haiku_or_not(sentence):
    haiku=[]
    sentence_words=sentence.split()
    sentence_syllables=[nsyl(word)[0] for word in sentence_words]
    syl_sum = np.cumsum(sentence_syllables) 
    if syl_sum[-1]==17 and 5 in syl_sum and 12 in syl_sum:
        print '\n'
        print article['cite']
        print article.get('DI',[''])[0]
        line=[]
        for idx,item in enumerate(syl_sum):
            line.append(sentence_words[idx])
            if item in [5,12,17]:
                line=' '.join(line)
                print line
                haiku.append(line)
                line=[]
    return haiku