import nltk
import sys
import string
import re
text = open('test.txt').read()
text = ' '.join(re.findall('[%s]+' % string.ascii_letters, text))

# Used when tokenizing words
sentence_re = r'''(?x)      # set flag to allow verbose regexps
      ([A-Z])(\.[A-Z])+\.?  # abbreviations, e.g. U.S.A.
    | \w+(-\w+)*            # words with optional internal hyphens
    | \$?\d+(\.\d+)?%?      # currency and percentages, e.g. $12.40, 82%
    | \.\.\.                # ellipsis
    | [][.,;"'?():-_`]      # these are separate tokens
'''

lemmatizer = nltk.WordNetLemmatizer()
stemmer = nltk.stem.porter.PorterStemmer()

#Taken from Su Nam Kim Paper...
grammar = r"""
    NBAR:
        {<NN.*|JJ>*<NN.*>}  # Nouns and Adjectives, terminated with Nouns

    NP:
        {<NBAR>}
        {<NBAR><IN><NBAR>}  # Above, connected with in/of/etc...
"""
chunker = nltk.RegexpParser(grammar)

toks = nltk.regexp_tokenize(text, sentence_re)
postoks = nltk.tag.pos_tag(toks)


tree = chunker.parse(postoks)

from nltk.corpus import stopwords
stopwords = stopwords.words('english')


def leaves(tree):
    """Finds NP (nounphrase) leaf nodes of a chunk tree."""
    for subtree in tree.subtrees(filter = lambda t: t.label()=='NP'):
        yield subtree.leaves()

def normalise(word):
    """Normalises words to lowercase and stems and lemmatizes it."""
    word = word.lower()
    #word = stemmer.stem_word(word)
    word = lemmatizer.lemmatize(word)
    return word

def acceptable_word(word):
    """Checks conditions for acceptable word: length, stopword."""
    accepted = bool(2 <= len(word) <= 40
        and word.lower() not in stopwords)
    return accepted


def get_terms(tree):
    for leaf in leaves(tree):
        term = [ normalise(w) for w,t in leaf if acceptable_word(w) ]
        yield term

terms = get_terms(tree)

from collections import Counter
c = Counter([word[0] for word in list(terms) if len(word)])
print c.most_common(5)